© 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-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 10790
    Prev
    Next
    INDEX
    Explanations

    the presence of phrases indicating origins or sources of actions

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

    "from"

    np_acts-logits-general · gemini-2.0-flash

    source of

    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
     serializers
    -0.35
     engines
    -0.33
    Biografía
    -0.33
    iformes
    -0.31
     ris
    -0.31
     présidentielle
    -0.30
     académica
    -0.30
     darauf
    -0.30
    adaran
    -0.30
    uttgart
    -0.30
    POSITIVE LOGITS
    fromnode
    0.79
     from
    0.77
     vanuit
    0.71
    from
    0.70
     FROM
    0.69
     From
    0.69
    จาก
    0.68
    From
    0.68
     từ
    0.64
     Administrativna
    0.64
    Activations Density 0.447%

    No Known Activations