© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 17-GEMMASCOPE-RES-16K
    6. 6790
    Prev
    Next
    INDEX
    Explanations

    terms related to technology, programming, and specific software usage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .
    -0.70
    h
    -0.70
     and
    -0.67
    b
    -0.65
    u
    -0.62
     is
    -0.59
    is
    -0.59
    and
    -0.57
    H
    -0.57
    a
    -0.57
    POSITIVE LOGITS
    SequentialGroup
    1.41
    tagHelperRunner
    1.30
     itſelf
    1.28
    __":
    
    1.27
    ſelves
    1.24
     وتسجيلات
    1.22
    )*/
    1.21
    styleType
    1.20
     myſelf
    1.19
    />";
    1.18
    Activations Density 0.146%

    No Known Activations