© 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. 20-GEMMASCOPE-RES-131K
    11. 63523
    Prev
    Next
    INDEX
    Explanations

    punctuation, particularly commas and periods, indicating a focus on sentence structure

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

    end of sentence punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    StyleSheet
    -0.46
     StyleSheet
    -0.44
     Basque
    -0.43
    Aix
    -0.41
    Spre
    -0.40
    Dres
    -0.39
    UnityEngine
    -0.39
    King
    -0.39
     vito
    -0.39
    stateMutability
    -0.38
    POSITIVE LOGITS
    脚注の使い方
    0.45
     defaultstate
    0.45
    MigrationBuilder
    0.44
    სქოლიო
    0.43
    +:+
    0.42
     casais
    0.41
    ⟬
    0.41
     devront
    0.39
    appareil
    0.39
     devraient
    0.39
    Activations Density 0.045%

    No Known Activations