© 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. 23-GEMMASCOPE-RES-16K
    11. 15264
    Prev
    Next
    INDEX
    Explanations

    specific instances and situations that highlight difficulties or challenges

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arschijnlijk
    -0.63
     nahilalakip
    -0.58
    windowFixed
    -0.57
    ---|---|
    -0.53
    BorderFactory
    -0.52
     &___
    -0.50
    それと
    -0.46
    theless
    -0.46
     ProtoMessage
    -0.46
    kelijkheid
    -0.46
    POSITIVE LOGITS
     where
    4.35
    where
    3.71
    Where
    3.07
     donde
    3.02
     Where
    3.01
     où
    2.90
     WHERE
    2.87
     где
    2.60
    WHERE
    2.50
    donde
    2.45
    Activations Density 1.765%

    No Known Activations