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. 20-GEMMASCOPE-RES-16K
    6. 6694
    Prev
    Next
    INDEX
    Explanations

    references to trees and their variations in context

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

    "tree" or variations of it

    np_acts-logits-general · gemini-2.0-flash

    tree and related concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
     Jefus
    -0.93
     myſelf
    -0.90
     pleaſure
    -0.85
    ñores
    -0.85
     ſeveral
    -0.84
     <=",
    -0.84
     themſelves
    -0.84
    UnsafeEnabled
    -0.83
     Majefty
    -0.83
    theless
    -0.82
    POSITIVE LOGITS
     Trees
    0.64
     trees
    0.64
     ​​
    0.59
    house
    0.58
     trunk
    0.57
     branches
    0.56
     trunks
    0.55
     branch
    0.55
    tops
    0.54
    e
    0.52
    Activations Density 0.112%

    No Known Activations