© 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. 10-GEMMASCOPE-RES-16K
    11. 8918
    Prev
    Next
    INDEX
    Explanations

    SQL query components and parameters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tonsoft
    -0.64
    OGND
    -0.56
    ymce
    -0.54
    copal
    -0.54
    ährlich
    -0.53
    FunctionFlags
    -0.53
    __(/*!
    -0.52
    arraycopy
    -0.52
     Extragalactic
    -0.51
     esternos
    -0.51
    POSITIVE LOGITS
    complexContent
    0.76
    richTextPanel
    0.67
    SharedCtor
    0.63
    ?,?,
    0.58
    IntoConstraints
    0.58
    msgTypes
    0.53
     prête
    0.52
     disponibilità
    0.52
    LookAnd
    0.52
    tokio
    0.51
    Activations Density 0.068%

    No Known Activations