© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 23-GEMMASCOPE-RES-16K
    11. 2238
    Prev
    Next
    INDEX
    Explanations

    phrases related to ranges and classifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ligiloj
    -0.59
    出版年
    -0.51
    getOutputStream
    -0.40
    canActivate
    -0.40
    MotionEvent
    -0.39
    toMatchSnapshot
    -0.37
     endfor
    -0.36
    linearGradient
    -0.36
     propOrder
    -0.36
    WebMethod
    -0.34
    POSITIVE LOGITS
    tanleria
    0.48
    rój
    0.46
     raisonnable
    0.44
    🇶
    0.43
     deepest
    0.43
    copyWith
    0.42
    centred
    0.42
    ratislava
    0.42
     utafitiHapana
    0.42
     Guadalajara
    0.42
    Activations Density 0.587%

    No Known Activations