© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 19-GEMMASCOPE-RES-16K
    6. 2347
    Prev
    Next
    INDEX
    Explanations

    specific programming functions and software-related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .
    -0.70
    ,
    -0.69
    -
    -0.60
    InstanceState
    -0.57
    a
    -0.57
    c
    -0.55
    es
    -0.54
    ;
    -0.53
    m
    -0.53
    !
    -0.52
    POSITIVE LOGITS
    ſelves
    1.48
    ſelf
    1.42
    neſs
    1.35
    wiſe
    1.31
     Roskov
    1.29
    \<^
    1.28
    Personensuche
    1.24
     houſe
    1.24
    BibitemShut
    1.23
    dafx
    1.23
    Activations Density 0.537%

    No Known Activations