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-2-2B
    4. Residual Stream - 16k
    5. 4-GEMMASCOPE-RES-16K
    6. 696
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to the concept of language and its components

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Bakgrunnsstoff
    -0.69
     ComVisible
    -0.66
     ostavi
    -0.66
     initComponents
    -0.66
    IUrlHelper
    -0.65
    tvguidetime
    -0.65
     незавершена
    -0.61
    sidemargin
    -0.61
     poffe
    -0.61
     AspNetCore
    -0.60
    POSITIVE LOGITS
     words
    2.16
     word
    2.12
     Words
    1.96
    Words
    1.88
     WORDS
    1.80
    words
    1.73
    word
    1.73
     Word
    1.69
    Word
    1.66
     WORD
    1.59
    Activations Density 0.322%

    No Known Activations