© 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. 22-GEMMASCOPE-RES-16K
    6. 8257
    Prev
    Next
    INDEX
    Explanations

    HTML and JavaScript elements and tags

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

    Characters often preceding file extensions

    np_acts-logits-general · gemini-2.0-flash

    javascript and html code

    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
     off
    -0.44
    #+#
    -0.44
     níveis
    -0.41
    товано
    -0.41
    angé
    -0.41
    이블
    -0.40
     titre
    -0.40
     levels
    -0.39
    ctez
    -0.39
    off
    -0.39
    POSITIVE LOGITS
     ModelExpression
    0.71
    ArgsConstructor
    0.66
    tonsoft
    0.66
     AssemblyCulture
    0.66
     InputDecoration
    0.63
     MainAxisSize
    0.63
     getItemId
    0.63
    Portale
    0.63
    AndEndTag
    0.62
     Wicidata
    0.62
    Activations Density 0.115%

    No Known Activations