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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 0-GEMMASCOPE-RES-16K
    6. 7407
    Prev
    Next
    INDEX
    Explanations

    code metadata and attribute declarations in source code fragments and configuration details

    oai_token-act-pair · o3-miniTriggered by @yemengyus1

    references to assembly attributes and properties in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     
    -2.27
     (
    -2.10
    ,
    -2.02
    .
    -1.89
    <eos>
    -1.80
     in
    -1.77
    -
    -1.75
    ↵
    -1.73
     I
    -1.71
    ↵↵
    -1.69
    POSITIVE LOGITS
     myſelf
    4.93
     Efq
    4.72
     itſelf
    4.71
     Monfieur
    4.68
     Theſe
    4.41
     Jefus
    4.26
     ―――――
    4.07
     ſeveral
    4.03
     themſelves
    4.03
     againſt
    4.00
    Activations Density 6.635%

    No Known Activations