© 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. 15-GEMMASCOPE-RES-16K
    11. 12653
    Prev
    Next
    INDEX
    Explanations

    direct quotes, statements, or reported speech

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Autoritní
    -0.79
    المشاركات
    -0.75
     AssemblyCulture
    -0.71
    )++;
    -0.67
    InitVars
    -0.67
     للمعارف
    -0.66
    ớm
    -0.63
    UnusedPrivate
    -0.62
    出版年
    -0.62
    soort
    -0.62
    POSITIVE LOGITS
     ostavi
    0.47
    ULTURE
    0.45
    flashdata
    0.43
     MIR
    0.41
    decer
    0.41
    ніципалі
    0.40
     ActivatedRoute
    0.40
    랬
    0.40
    :“
    0.40
     charset
    0.40
    Activations Density 0.109%

    No Known Activations