© 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. 41-GEMMASCOPE-RES-16K
    6. 7599
    Prev
    Next
    INDEX
    Explanations

    structured code elements and data structures used in programming languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    </h6>
    -1.69
    </h3>
    -1.51
    </h5>
    -1.48
    </u>
    -1.24
    </h4>
    -1.18
    "}>
    -1.05
    "},
    
    -1.05
    '}>
    -1.02
    ']}
    -1.02
    "]}
    -1.02
    POSITIVE LOGITS
    <h2>
    0.84
     astore
    0.48
    end
    0.45
     mxArray
    0.38
    </b>
    0.36
    machung
    0.36
     pét
    0.35
    adaptiveStyles
    0.34
    </blockquote>
    0.34
    ikistan
    0.34
    Activations Density 0.143%

    No Known Activations