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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 18-GEMMASCOPE-RES-16K
    6. 1166
    Prev
    Next
    INDEX
    Explanations

    function calls related to output and string manipulation

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

    String concatenation or formatting within code

    np_acts-logits-general · gemini-2.0-flash

    building formatted strings

    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
     danni
    -0.48
     mxArray
    -0.47
    Revenir
    -0.47
    addContainerGap
    -0.46
    azole
    -0.46
    MessageWindow
    -0.46
    endregion
    -0.46
    %>
    -0.43
     aDecoder
    -0.43
    WithError
    -0.43
    POSITIVE LOGITS
    CloseOperation
    0.72
    WriteLiteral
    0.70
    awtextra
    0.65
     OMITBAD
    0.59
    Hozzáférés
    0.57
     Efq
    0.57
    Архівовано
    0.57
    Einzelnachweise
    0.55
    esteld
    0.54
    >[
    0.53
    Activations Density 0.088%

    No Known Activations