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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 20-GEMMASCOPE-RES-16K
    6. 1490
    Prev
    Next
    INDEX
    Explanations

    lines of code with function declarations or error handling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "this" in code

    np_acts-logits-general · gemini-2.0-flash

    $this

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ban
    -0.46
    شون
    -0.44
    isma
    -0.44
    o
    -0.43
    /**/*.
    -0.43
     همان
    -0.42
    那是
    -0.42
    an
    -0.42
    لسط
    -0.42
     testGet
    -0.42
    POSITIVE LOGITS
     this
    2.93
    this
    2.60
     này
    1.69
     THIS
    1.66
    This
    1.64
     This
    1.58
     questa
    1.56
     questo
    1.55
     этого
    1.50
    THIS
    1.50
    Activations Density 0.096%

    No Known Activations