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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 8539
    Prev
    Next
    INDEX
    Explanations

    metadata related to language and translation

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

    HTML language tags followed by "en"

    np_acts-logits-general · gemini-2.0-flash

    country and language codes

    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
    IndentedString
    -0.56
    Xna
    -0.56
    __*/
    -0.55
    migrationBuilder
    -0.55
    msgTypes
    -0.54
     صوتيه
    -0.54
    astify
    -0.52
    WriteLiteral
    -0.52
     ExecuteAsync
    -0.51
     sekali
    -0.50
    POSITIVE LOGITS
     fr
    0.70
    ru
    0.67
    RU
    0.65
    fr
    0.63
     RU
    0.60
    hu
    0.58
     nl
    0.58
     NL
    0.57
    de
    0.56
    nl
    0.54
    Activations Density 0.266%

    No Known Activations