© 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-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 8771
    Prev
    Next
    INDEX
    Explanations

    phrases indicating frequency or typicality in actions or events

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

    Adverbs of probability/frequency

    np_acts-logits-general · gemini-2.0-flash

    adverbs of possibility and frequency

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     samostat
    -0.38
     dreapta
    -0.36
     actualidad
    -0.36
    JsonPropertyName
    -0.36
     independencia
    -0.35
     vigencia
    -0.35
     helg
    -0.35
     instrucción
    -0.35
    AutoModerator
    -0.34
    acier
    -0.34
    POSITIVE LOGITS
    ValueStyle
    0.69
     AssemblyCulture
    0.67
    QMetaType
    0.63
     للاسماء
    0.60
    Попис
    0.56
    expandindo
    0.56
    RectangleBorder
    0.55
     nakalista
    0.53
    enumii
    0.53
    GOTREF
    0.53
    Activations Density 0.705%

    No Known Activations