© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 13312
    Prev
    Next
    INDEX
    Explanations

    key phrases that indicate change and its consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    migrationBuilder
    -0.62
    enderror
    -0.61
    مصادر
    -0.56
    }\]
    -0.51
     RUE
    -0.48
     gelt
    -0.46
     simultaneously
    -0.46
    }));
    -0.46
     ↑
    -0.44
    AddHtmlAttribute
    -0.44
    POSITIVE LOGITS
     entière
    0.67
     slightest
    0.66
     suffit
    0.64
    knię
    0.62
     alone
    0.62
     Allein
    0.59
     wystarczy
    0.58
     saja
    0.56
    avyzd
    0.56
     semplice
    0.56
    Activations Density 0.322%

    No Known Activations