© 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 - 65k
    5. 13-GEMMASCOPE-RES-65K
    6. 15778
    Prev
    Next
    INDEX
    Explanations

    parameters and variables in coding contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     GoogleFonts
    -0.76
    Portale
    -0.75
     povezave
    -0.73
    trise
    -0.70
    Hozzáférés
    -0.69
    躇
    -0.66
    rister
    -0.65
    ittarius
    -0.65
    mberto
    -0.65
    rungsseite
    -0.65
    POSITIVE LOGITS
    RenderAtEndOf
    0.73
    AutoresizingMask
    0.49
     esternos
    0.47
    IonicModule
    0.47
    LogFactory
    0.43
    httphttps
    0.40
     ModelAndView
    0.40
     and
    0.39
     />);
    0.39
    tagHelperRunner
    0.38
    Activations Density 0.028%

    No Known Activations