© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 23-GEMMASCOPE-RES-16K
    11. 9288
    Prev
    Next
    INDEX
    Explanations

    technical keywords and identifiers related to coding and programming structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     aveug
    -0.51
    ostante
    -0.51
    צלחה
    -0.49
    InSection
    -0.47
     valable
    -0.47
     confund
    -0.45
     détect
    -0.45
     kazi
    -0.43
     coupable
    -0.42
    entibus
    -0.42
    POSITIVE LOGITS
     CreateTagHelper
    0.98
    SourceChecksum
    0.92
    migrationBuilder
    0.82
    بوابة
    0.79
     Мексичка
    0.79
     дописавши
    0.78
    parsedMessage
    0.78
    पया
    0.78
    WebElementEntity
    0.77
    脚注の使い方
    0.76
    Activations Density 0.448%

    No Known Activations