© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 8914
    Prev
    Next
    INDEX
    Explanations

    expressions of surprise or realization

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

    expressions of personal amazement or surprise at something unexpected.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RefNanny
    -0.45
    RenderAtEndOf
    -0.44
     CreateTagHelper
    -0.43
    farb
    -0.39
    хьтан
    -0.37
    беріга
    -0.34
    drawSprites
    -0.33
    adpleegd
    -0.33
     teş
    -0.33
    лтемелер
    -0.32
    POSITIVE LOGITS
     how
    1.81
    how
    1.21
    どれだけ
    1.02
     چقدر
    1.01
     насколько
    1.00
    How
    0.99
     combien
    0.99
     cuánto
    0.98
     hoeveel
    0.96
    いかに
    0.94
    Activations Density 0.343%

    No Known Activations