Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 74514
    Prev
    Next
    INDEX
    Explanations

    JavaScript variable declarations and AngularJS scope references

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

    scope in code

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    astify
    -0.57
    ElementException
    -0.42
     configureStore
    -0.40
    RectangleBorder
    -0.37
    __*/
    -0.34
    FailureListener
    -0.34
     erhi
    -0.34
     folos
    -0.33
     waard
    -0.33
    Trọng
    -0.32
    POSITIVE LOGITS
    scope
    1.32
     scope
    1.09
    Scope
    1.04
    SCOPE
    0.93
     Scope
    0.93
     SCOPE
    0.83
    rootScope
    0.82
     scopes
    0.81
    scopes
    0.75
     OnInit
    0.63
    Activations Density 0.005%

    No Known Activations