Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 10
    Prev
    Next
    INDEX
    Explanations

    references to alcoholic beverages and desserts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    food and drink-related items, particularly wines, beers, and specific dishes.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi

    Text highlights specific food and drink items typically associated with dining experiences, focusing on various cuisines and the availability of beverages in restaurants and online settings.

    eleuther_acts_top20 · gpt-4o-miniTriggered by @neilrathi

    beverages and drinks, particularly alcoholic ones, along with related terms like descriptions of wine or beer lists.

    oai_token-act-pair · gpt-4oTriggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CreateTagHelper
    -0.74
    期刊论文
    -0.71
    ementara
    -0.68
     beſch
    -0.67
    AddTagHelper
    -0.66
     ſelbſt
    -0.64
    ſelben
    -0.64
     beſte
    -0.63
     unſer
    -0.63
    Filmographie
    -0.63
    POSITIVE LOGITS
     drinks
    0.40
     wine
    0.39
     drink
    0.36
     water
    0.31
    CopyWith
    0.30
     beer
    0.28
     drinking
    0.26
     Numerade
    0.25
    Drinks
    0.24
     glasses
    0.24
    Activations Density 0.036%

    No Known Activations