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. 21-GEMMASCOPE-RES-16K
    6. 1500
    Prev
    Next
    INDEX
    Explanations

    file paths and identifiers related to source and script files

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IntoConstraints
    -0.49
     للمعارف
    -0.49
     obstante
    -0.37
    moveToFirst
    -0.36
     typelib
    -0.36
     مشين
    -0.36
    dyž
    -0.35
     timeType
    -0.34
    듦
    -0.34
    yych
    -0.34
    POSITIVE LOGITS
    ⓧ
    0.57
     "..\..\..\
    0.52
    balleur
    0.51
     "..\..\
    0.49
     Numerade
    0.48
     defaultstate
    0.48
     ◄
    0.46
    founded
    0.45
     Flesh
    0.45
     './../
    0.44
    Activations Density 0.186%

    No Known Activations