© 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 - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 66259
    Prev
    Next
    INDEX
    Explanations

    references to programming constructs related to protocol buffers in the Swift programming language

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

    proto: string fields

    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
     виправивши
    -0.34
    Garantía
    -0.30
     cashier
    -0.29
     administrador
    -0.29
     recibo
    -0.29
     захо
    -0.28
     Wahr
    -0.28
    Administrador
    -0.28
    帖最后由
    -0.27
     पर्
    -0.27
    POSITIVE LOGITS
    proto
    3.67
     proto
    3.09
    Proto
    2.83
     Proto
    2.75
     PROTO
    2.27
    PROTO
    2.14
     прото
    1.91
     prototypes
    1.79
    protos
    1.75
     prototype
    1.66
    Activations Density 0.016%

    No Known Activations