© 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. 25-GEMMASCOPE-RES-16K
    6. 10766
    Prev
    Next
    INDEX
    Explanations

    sequences or patterns of characters, likely pertaining to coding or programming syntax

    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
     kasarigan
    -0.68
    orm
    -0.58
    igure
    -0.57
    fvar
    -0.55
    ciutto
    -0.55
    клопе
    -0.55
    ul
    -0.55
    /******/
    -0.55
    verwijspagina
    -0.54
    prior
    -0.54
    POSITIVE LOGITS
    VersionUID
    0.56
    FirstResponder
    0.50
    ep
    0.49
    fromLTRB
    0.47
    )|^{
    0.46
     rând
    0.45
    numerusform
    0.45
    CodedInputStream
    0.44
    ian
    0.44
    uo
    0.43
    Activations Density 0.409%

    No Known Activations