© 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. 10933
    Prev
    Next
    INDEX
    Explanations

    code structure elements such as class and method declarations

    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
    fromnode
    -0.69
    </strong>
    -0.66
     betweenstory
    -0.62
    SharedDtor
    -0.57
    verwijspagina
    -0.57
     autorytatywna
    -0.55
    حياتها
    -0.53
     صوتيه
    -0.52
    ℗
    -0.50
    $.}
    -0.48
    POSITIVE LOGITS
     LoggerFactory
    0.59
     فريبيس
    0.56
    principalColumn
    0.55
    UrlResolution
    0.55
    atigable
    0.55
    esseurs
    0.53
    <b>
    0.53
    fflush
    0.51
    UpInside
    0.50
     }}"></
    0.50
    Activations Density 0.036%

    No Known Activations