© 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. 7-GEMMASCOPE-RES-16K
    6. 14081
    Prev
    Next
    INDEX
    Explanations

    references to file paths and binary files

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nakalista
    -1.06
    ьаж
    -0.97
    ThroughAttribute
    -0.96
    XmlAccessorType
    -0.83
     AssemblyCulture
    -0.83
    abestanden
    -0.81
    migrationBuilder
    -0.81
    velocityY
    -0.81
    +#+
    -0.79
     Ife
    -0.75
    POSITIVE LOGITS
     bin
    1.79
    bin
    1.67
     Bin
    1.63
     BIN
    1.60
    Bin
    1.51
    BIN
    1.48
     bins
    1.46
     Bins
    1.28
    Bins
    1.17
    bins
    1.11
    Activations Density 0.149%

    No Known Activations