© 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. 1-GEMMASCOPE-RES-16K
    6. 5050
    Prev
    Next
    INDEX
    Explanations

    terms related to statistical inference and regression analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tvguidetime
    -0.74
    drawSprites
    -0.65
     FetchType
    -0.62
     ***/
    -0.61
    expandindo
    -0.57
    Trayectoria
    -0.55
     recensement
    -0.55
    ậu
    -0.54
     estekak
    -0.54
    athione
    -0.54
    POSITIVE LOGITS
     ExecuteAsync
    0.68
     Kings
    0.64
     ABC
    0.57
    Monkey
    0.56
    MessageOf
    0.55
    prnewswire
    0.53
    monkey
    0.53
     KINGS
    0.52
    ContentAsync
    0.52
     Johnny
    0.51
    Activations Density 2.078%

    No Known Activations