© 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. 8-GEMMASCOPE-RES-16K
    6. 15350
    Prev
    Next
    INDEX
    Explanations

    API-related terms and methods along with their parameters in Java

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/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.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Signalez
    -0.59
    ấc
    -0.58
    >--}}
    -0.51
    UnknownFields
    -0.50
    saraba
    -0.49
    GOTREF
    -0.49
    ariable
    -0.49
    ')";
    -0.49
    maline
    -0.48
     Winter
    -0.48
    POSITIVE LOGITS
    DockStyle
    0.67
    Geplaatst
    0.67
    igshid
    0.61
    ?,?,
    0.58
    ècie
    0.55
    WRENCE
    0.54
    djangoproject
    0.52
    Ljava
    0.52
     slike
    0.50
    جمعیت
    0.50
    Activations Density 0.182%

    No Known Activations