© 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. 19-GEMMASCOPE-RES-16K
    6. 629
    Prev
    Next
    INDEX
    Explanations

    technical instructions related to software settings and configurations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    angliski
    -0.60
    encodeWith
    -0.57
    IsPostBack
    -0.49
    __':
    -0.49
    AutoresizingMask
    -0.49
    larıyla
    -0.48
    larla
    -0.48
    initComponents
    -0.48
    Spoljašnje
    -0.47
    nost
    -0.47
    POSITIVE LOGITS
     click
    1.16
    click
    0.91
     clicking
    0.91
     Click
    0.89
     scroll
    0.86
     select
    0.84
    Click
    0.84
     clicked
    0.83
     CLICK
    0.79
    点击
    0.79
    Activations Density 0.176%

    No Known Activations