Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 16-GEMMASCOPE-RES-65K
    6. 53337
    Prev
    Next
    INDEX
    Explanations

    phrases related to data availability and accessibility

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

    PA

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TagHelper
    -0.56
     außen
    -0.54
    #+#
    -0.50
    Bakgrunnsstoff
    -0.48
    ?";
    -0.47
    úp
    -0.47
    !";
    -0.44
     fleuve
    -0.44
     Küste
    -0.44
     باخ
    -0.44
    POSITIVE LOGITS
     становника
    1.06
    contentLoaded
    0.91
    исленность
    0.83
    IsMutable
    0.79
    InjectAttribute
    0.75
    Хро
    0.70
    kháu
    0.69
     Roskov
    0.68
    migrationBuilder
    0.68
    Népesség
    0.68
    Activations Density 0.000%

    No Known Activations