© 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. 15-GEMMASCOPE-RES-16K
    11. 4203
    Prev
    Next
    INDEX
    Explanations

    variables and their assignments in a programming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Hilde
    -0.56
     useContext
    -0.54
     sàng
    -0.54
     cjs
    -0.53
    MID
    -0.53
     sachant
    -0.52
    hicles
    -0.52
    __.__
    -0.52
    ConfigureAwait
    -0.52
    ::::::::
    -0.51
    POSITIVE LOGITS
    Referanser
    0.61
    Przypisy
    0.59
    Дереккөздер
    0.58
     ProtoMessage
    0.56
    Izvori
    0.53
    Aholisi
    0.52
    Bakgrunnsstoff
    0.52
    ఔ
    0.52
    +#+#
    0.51
    IntoConstraints
    0.51
    Activations Density 0.246%

    No Known Activations