© 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-2-2B
    7. Residual Stream - 16k
    9. 12-GEMMASCOPE-RES-16K
    11. 6982
    Prev
    Next
    INDEX
    Explanations

    structured programming elements such as function definitions and variable declarations

    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
    Tikang
    -0.94
    StructEnd
    -0.91
    évaluateur
    -0.89
     Efq
    -0.87
     Houſe
    -0.84
    Rüyada
    -0.82
    neſs
    -0.81
     ſur
    -0.81
    ⓧ
    -0.81
     itſelf
    -0.80
    POSITIVE LOGITS
    ↵↵
    0.63
    ↵
    0.59
    </blockquote>
    0.47
    ↵↵↵
    0.47
    shortcuts
    0.43
     refiere
    0.43
    </h5>
    0.42
    __":
    0.42
    </h3>
    0.42
     Audiodateien
    0.41
    Activations Density 0.202%

    No Known Activations