© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 6237
    Prev
    Next
    INDEX
    Explanations

    phrases that emphasize precision, importance, or specific details in the text

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

    preceding commas or conjunctions

    np_acts-logits-general · gemini-2.0-flash

    linking clauses and ideas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    \"");
    -0.62
     kasarigan
    -0.61
    )"),
    -0.61
    )";
    -0.59
     لينك
    -0.59
    )");
    -0.59
    "");
    -0.59
    ſicht
    -0.57
     BIC
    -0.57
    "}},
    -0.57
    POSITIVE LOGITS
    первых
    0.62
    ,
    0.54
     obstante
    0.49
     Nevertheless
    0.47
    Javadoc
    0.47
    Nevertheless
    0.45
     vandens
    0.41
    Ikus
    0.41
    Accordingly
    0.40
    来讲
    0.40
    Activations Density 0.720%

    No Known Activations