© 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. 3-GEMMASCOPE-RES-16K
    6. 5547
    Prev
    Next
    INDEX
    Explanations

    statements about obligations or requirements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    apimachinery
    -0.53
    脚注の使い方
    -0.50
    usercontent
    -0.45
    optionalTypeArgs
    -0.43
     implications
    -0.43
    ípios
    -0.43
    TypedDataSet
    -0.42
     distinción
    -0.42
     Träger
    -0.42
     Implications
    -0.42
    POSITIVE LOGITS
     shall
    0.64
    """
    0.56
     """
    0.54
     SHALL
    0.54
     Shall
    0.53
    """
    
    0.52
    就是要
    0.51
    shall
    0.51
    EndInit
    0.51
    ."""
    0.50
    Activations Density 0.067%

    No Known Activations