© 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 EvalsExportsinterp-engineNEWAPI 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. 8360
    Prev
    Next
    INDEX
    Explanations

    references to specific events or actions taken by characters

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

    Sentai robot finisher moves

    np_acts-logits-general · gemini-2.0-flash

    finisher moves

    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
     GenerationType
    -0.49
    oredCriteria
    -0.45
    CPtr
    -0.44
    makeText
    -0.44
    MigrationBuilder
    -0.43
     externi
    -0.42
    ChildScrollView
    -0.41
    /*---
    -0.41
    Искәрмәләр
    -0.40
    CppMethod
    -0.40
    POSITIVE LOGITS
     pose
    0.81
     poses
    0.80
     gestures
    0.74
     gesture
    0.74
     posture
    0.69
     dance
    0.68
     maneuvers
    0.67
     postures
    0.65
     motions
    0.62
     gestes
    0.62
    Activations Density 0.414%

    No Known Activations