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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 15467
    Prev
    Next
    INDEX
    Explanations

    technical code elements, specifically related to JavaScript libraries and frameworks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Text after the number zero

    np_acts-logits-general · gemini-2.0-flash

    descriptive phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     <<<<<<<<<<<<<<
    -0.48
    Conteúdo
    -0.45
     chiusura
    -0.44
     bedo
    -0.43
     in
    -0.41
     that
    -0.40
     meant
    -0.39
     étan
    -0.39
     extended
    -0.39
     corretamente
    -0.38
    POSITIVE LOGITS
    rxjs
    1.05
     يتيمه
    0.96
     GenerationType
    0.92
    AnchorStyles
    0.89
    principalColumn
    0.84
    '],
    0.83
    出版年
    0.82
    zzleHttp
    0.81
    `,
    0.80
    Hochspringen
    0.78
    Activations Density 0.038%

    No Known Activations