© 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. 8-GEMMASCOPE-RES-16K
    6. 7796
    Prev
    Next
    INDEX
    Explanations

    key mathematical symbols and notations relevant to statistics and data analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GraphicsUnit
    -0.59
    addCriterion
    -0.57
    StoryboardSegue
    -0.55
     hjelp
    -0.53
    addGap
    -0.52
    iconque
    -0.52
    fjspx
    -0.51
     allmän
    -0.50
     ffilmiau
    -0.50
    tagHelperRunner
    -0.48
    POSITIVE LOGITS
    msgSender
    0.56
     '\\;'
    0.56
     daran
    0.55
    ubri
    0.54
     newOwner
    0.52
    inaudible
    0.51
    RenderTarget
    0.51
    PRESA
    0.50
    grind
    0.50
     ldc
    0.50
    Activations Density 0.521%

    No Known Activations