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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 10-GEMMASCOPE-RES-16K
    6. 12656
    Prev
    Next
    INDEX
    Explanations

    processes and function calls in programming code.

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    LookAnd
    -1.13
    Datuak
    -1.04
    fjspx
    -1.04
    RenderAtEndOf
    -0.96
    :✨
    -0.96
    MemoryWarning
    -0.86
    ViewFeatures
    -0.86
    istoitu
    -0.84
     فريبيس
    -0.83
    InjectAttribute
    -0.82
    POSITIVE LOGITS
    #!/
    0.46
     c
    0.41
     hoy
    0.41
     nada
    0.40
     viện
    0.39
     e
    0.38
     in
    0.38
     io
    0.38
    nie
    0.37
     on
    0.37
    Activations Density 0.778%

    No Known Activations