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. 19-GEMMASCOPE-RES-16K
    6. 278
    Prev
    Next
    INDEX
    Explanations

    references to the concept of "hash" or "assassins."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/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.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RuleContext
    -0.83
    )`
    -0.70
    出版年
    -0.68
    Ска
    -0.65
    ränkt
    -0.65
    etern
    -0.64
    iedenen
    -0.63
    mtrl
    -0.63
     Solitude
    -0.63
     AspNetCore
    -0.63
    POSITIVE LOGITS
    ash
    0.86
    ASH
    0.81
     Tash
    0.72
     ASH
    0.70
     Mash
    0.70
    Ash
    0.70
     Ash
    0.69
     Osh
    0.68
     Tosh
    0.65
    Mash
    0.64
    Activations Density 0.132%

    No Known Activations