© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 25-GEMMASCOPE-RES-16K
    11. 16050
    Prev
    Next
    INDEX
    Explanations

    references to a specific individual or entity named "Hal."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     <=",
    -0.83
    principalTable
    -0.65
    yntaxException
    -0.59
    esModule
    -0.58
    AutoField
    -0.58
    حياتها
    -0.56
     comuniques
    -0.56
    elemField
    -0.55
    //</
    -0.54
    oneofs
    -0.53
    POSITIVE LOGITS
    \{\\
    0.69
    InitVars
    0.56
    cyon
    0.55
    lujah
    0.53
    ibut
    0.53
    ucin
    0.52
    IDAY
    0.52
    ftone
    0.51
    ifax
    0.48
    Monitor
    0.48
    Activations Density 0.225%

    No Known Activations