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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 15-GEMMASCOPE-RES-16K
    6. 2130
    Prev
    Next
    INDEX
    Explanations

    terminology related to charting and user interface elements

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

    references to chart components and their attributes in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    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
    -1.10
    AccessorTable
    -1.10
    RegressionTest
    -1.06
    tagHelperRunner
    -1.03
    +#+#
    -1.02
    StoryboardSegue
    -0.97
     vectorstock
    -0.95
     myſelf
    -0.95
     nahilalakip
    -0.94
     disambiguazione
    -0.93
    POSITIVE LOGITS
     of
    0.63
    addContainerGap
    0.56
    /
    0.56
     to
    0.53
    ,
    0.52
     that
    0.51
     /
    0.51
    ;
    0.50
    .
    0.49
     in
    0.46
    Activations Density 0.341%

    No Known Activations