© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 2573
    Prev
    Next
    INDEX
    Explanations

    import statements in code-related contexts

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

    "from" followed by a module or library name

    np_acts-logits-general · gemini-2.0-flash

    import statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fVar
    -0.74
    AccessorTable
    -0.74
     فريبيس
    -0.73
     NSCoder
    -0.73
    GEBURTS
    -0.71
    LookAnd
    -0.69
     nakalista
    -0.69
    DockStyle
    -0.69
     juridiques
    -0.68
    saraba
    -0.67
    POSITIVE LOGITS
     .
    0.59
    NSNotification
    0.59
     ..
    0.55
     Sca
    0.52
    liothèque
    0.49
    brot
    0.47
     Вікіпе
    0.47
    …………………………………………
    0.47
     Rad
    0.47
     common
    0.46
    Activations Density 0.029%

    No Known Activations