© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 6415
    Prev
    Next
    INDEX
    Explanations

    programming terms and elements associated with HTML and JavaScript functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code snippets with "prototype", "function", or "cerr"

    np_acts-logits-general · gemini-2.0-flash

    prototype.prototype.prototype

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/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.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    on
    -0.63
    en
    -0.62
    c
    -0.61
    v
    -0.60
    ers
    -0.60
    er
    -0.59
    ens
    -0.59
    ing
    -0.59
    sel
    -0.58
    an
    -0.58
    POSITIVE LOGITS
     الحره
    0.95
     ModelExpression
    0.88
    存于互联网档案馆
    0.85
    CloseOperation
    0.81
     CreateTagHelper
    0.81
    ::_('
    0.81
     >=",
    0.79
     AssemblyTitle
    0.79
    <?
    0.78
    $_['
    0.76
    Activations Density 0.816%

    No Known Activations