© 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 - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 105742
    Prev
    Next
    INDEX
    Explanations

    technical elements related to programming and computational processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
    FirstResponder
    -0.30
    ">)</
    -0.30
    })));
    -0.29
    <>());
    -0.29
    ])){
    -0.28
    EndInit
    -0.28
    "]));
    -0.27
    новништво
    -0.27
    Unlike
    -0.27
    )}=\
    -0.26
    POSITIVE LOGITS
     يتيمه
    0.67
    SBATCH
    0.66
     ſind
    0.63
    ſchaft
    0.62
    ьаж
    0.61
    ThroughAttribute
    0.60
     NSCoder
    0.59
    expandindo
    0.58
     $_(
    0.58
     fashiola
    0.58
    Activations Density 0.140%

    No Known Activations