© 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
    7. Residual Stream - 16k
    9. 40-GEMMASCOPE-RES-16K
    11. 6176
    Prev
    Next
    INDEX
    Explanations

    technical terms, structured data formats, and programming constructs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    </em>
    -1.63
    </blockquote>
    -1.58
    </i>
    -1.45
    </h3>
    -1.34
    ';
    -1.16
    ";
    -1.14
    .";
    -1.13
    </h6>
    -1.11
     ";
    -1.05
    >";
    -1.02
    POSITIVE LOGITS
    ")
    1.68
    ")}
    1.55
     ")
    1.48
    ”)
    1.45
    ")
    1.41
     »)
    1.41
    ')
    1.40
    "),
    1.39
    ");
    1.38
    .")
    1.38
    Activations Density 0.700%

    No Known Activations