© 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-2-9B
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 10388
    Prev
    Next
    INDEX
    Explanations

    complex mathematical notations and scientific terminologies

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

    Mathematical or physics equations/notation

    np_acts-logits-general · gemini-2.0-flash

    indices paired with brackets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/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.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    __":
    -0.75
    ]")]
    -0.74
    transQ
    -0.73
    __':
    -0.72
    }}/>
    -0.68
    ]){
    -0.67
    }}">
    -0.66
    ]");
    -0.66
    .")]
    -0.66
    "]}
    -0.65
    POSITIVE LOGITS
     quelconque
    0.40
     publicidad
    0.39
    entraî
    0.37
     teritor
    0.37
     correcto
    0.37
    írus
    0.36
    accesso
    0.35
     ModelExpression
    0.34
     virgen
    0.34
     entraî
    0.34
    Activations Density 0.906%

    No Known Activations