© 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
    7. Residual Stream - 16k
    9. 37-GEMMASCOPE-RES-16K
    11. 3837
    Prev
    Next
    INDEX
    Explanations

    programming and coding structures or elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ")";
    -0.40
     ब्रेकडाउन
    -0.39
    </blockquote>
    -0.39
     ")");
    -0.38
    ¬
    -0.36
    vium
    -0.35
     "'");
    -0.35
    saraba
    -0.34
    ↵↵↵↵↵↵↵↵
    -0.34
    Искәрмәләр
    -0.34
    POSITIVE LOGITS
    1.34
    .

    1.06
    。

    1.05
    ?

    1.04
    !

    1.02
    ,

    0.98
    :

    0.93
    '

    0.87
     

    0.85
    ).

    0.84
    Activations Density 0.246%
    No Known Activations