© 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. 5932
    Prev
    Next
    INDEX
    Explanations

    phrases indicating different aspects or points of discussion

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

    Appears after certain words: is, of, major, point, important, second

    np_acts-logits-general · gemini-2.0-flash

    is

    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
     Photocase
    -0.44
     conmigo
    -0.38
     sèche
    -0.37
     exhausted
    -0.37
     kekasih
    -0.36
    trice
    -0.35
    ScopeManager
    -0.35
    かく
    -0.35
    ковь
    -0.35
     Stuhl
    -0.35
    POSITIVE LOGITS
    RTHOOK
    0.54
     ब्रेकडाउन
    0.52
    PointerException
    0.52
    bitField
    0.51
     Audiodateien
    0.49
    RectangleBorder
    0.49
    $_['
    0.48
    writeFieldEnd
    0.47
    queryInterface
    0.47
    LLocation
    0.47
    Activations Density 0.743%

    No Known Activations