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. 1-GEMMASCOPE-RES-16K
    6. 9727
    Prev
    Next
    INDEX
    Explanations

    file paths or directory structures within a Windows operating system context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Sist
    -0.78
     NTS
    -0.77
    ніципа
    -0.76
     coö
    -0.72
     gramm
    -0.71
     Centa
    -0.69
     Efq
    -0.69
     Kości
    -0.68
    ”…
    -0.67
    WireFormatLite
    -0.67
    POSITIVE LOGITS
    :\
    1.22
    :(
    0.77
    :/
    0.68
     ها
    0.63
    中海
    0.60
    untungan
    0.59
    (!__
    0.53
     Goodwin
    0.53
     :\
    0.52
     still
    0.52
    Activations Density 0.107%

    No Known Activations