© 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. 10581
    Prev
    Next
    INDEX
    Explanations

    references to different sides or perspectives in a discussion or analysis

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

    "Side" followed by "of"

    np_acts-logits-general · gemini-2.0-flash

    sides 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
    daction
    -0.40
    BASEPATH
    -0.40
    CodedInputStream
    -0.39
    rawDesc
    -0.38
    loadModel
    -0.38
    fetchone
    -0.38
     primary
    -0.38
    حوالہ
    -0.37
    createStatement
    -0.37
    Kariera
    -0.36
    POSITIVE LOGITS
     symmetrical
    0.75
     symmetric
    0.68
     sides
    0.68
     symmetry
    0.64
    symmetric
    0.63
    sides
    0.63
     Sides
    0.62
     Symmetric
    0.60
    Sides
    0.57
     flanking
    0.56
    Activations Density 0.543%

    No Known Activations