© 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. 0-GEMMASCOPE-RES-16K
    6. 9053
    Prev
    Next
    INDEX
    Explanations

    references to cursors and specific data management terms in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    antaranya
    -0.90
    GraphicsUnit
    -0.80
    adaptiveStyles
    -0.79
     snippetHide
    -0.79
    AnchorTagHelper
    -0.78
    __).
    -0.77
    LEncoder
    -0.77
    awaiter
    -0.74
    +#+
    -0.72
    CloseOperation
    -0.71
    POSITIVE LOGITS
    tor
    0.84
    TOR
    0.73
    otimes
    0.68
     torch
    0.65
    torch
    0.59
     stem
    0.59
     Torch
    0.57
     TOR
    0.54
    Torch
    0.53
     tor
    0.52
    Activations Density 0.082%

    No Known Activations