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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 0-GEMMASCOPE-RES-16K
    6. 2736
    Prev
    Next
    INDEX
    Explanations

    references to brick and glass materials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    нибудь
    -0.56
    热
    -0.53
     tuo
    -0.52
    leto
    -0.52
    }\}$
    -0.48
    </i>
    -0.48
    热的
    -0.47
    ,"
    -0.46
    exécution
    -0.46
    h
    -0.46
    POSITIVE LOGITS
     itſelf
    0.97
    Ctrl
    0.91
     juſ
    0.91
     faſt
    0.88
     raiſ
    0.87
     pleaſure
    0.85
     ſta
    0.84
     ctrl
    0.82
     Reſ
    0.81
     Anſ
    0.81
    Activations Density 0.102%

    No Known Activations