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. 22-GEMMASCOPE-RES-16K
    6. 11076
    Prev
    Next
    INDEX
    Explanations

    elements related to programming constructs such as variables, conditions, and dimensions in a coding context

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

    Code related to coordinates or positions (x, y)

    np_acts-logits-general · gemini-2.0-flash

    b or y after other b or y

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    </em>
    -0.54
     aged
    -0.49
     
    -0.47
     safety
    -0.46
    jí
    -0.46
    <eos>
    -0.45
     some
    -0.45
    httphttps
    -0.45
     ê
    -0.45
     itself
    -0.44
    POSITIVE LOGITS
    CloseOperation
    0.98
    yntaxException
    0.95
    Бахар
    0.88
     gainera
    0.88
     архивлан
    0.88
    Controllo
    0.87
    windowFixed
    0.86
    Jeografia
    0.86
     ditto
    0.86
    Vidite
    0.83
    Activations Density 0.777%

    No Known Activations