© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 5-GEMMASCOPE-RES-16K
    11. 10925
    Prev
    Next
    INDEX
    Explanations

    the "@" symbol, typically used for annotations or decorations in programming or technical writing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    وردار
    -0.60
    Filmographie
    -0.56
    .
    -0.46
     big
    -0.46
     sound
    -0.45
    big
    -0.45
     tek
    -0.43
    DoubleQuotes
    -0.43
    '
    -0.43
    uteur
    -0.42
    POSITIVE LOGITS
    TagMode
    1.22
    تقاوى
    1.06
    @
    1.02
     snippetHide
    1.02
     AssemblyCulture
    0.95
    addPreferredGap
    0.94
    awtextra
    0.92
    IsContent
    0.87
     мәкал
    0.86
    CodeAttribute
    0.78
    Activations Density 0.058%

    No Known Activations