© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 7-GEMMASCOPE-RES-16K
    11. 14987
    Prev
    Next
    INDEX
    Explanations

    terms related to safety and risk prevention in medical or procedural contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    reactstrap
    -0.47
     buscas
    -0.38
     profess
    -0.37
     prest
    -0.35
    Toponymie
    -0.34
     mariscos
    -0.34
    gangenheit
    -0.34
    endaft
    -0.34
    titanium
    -0.33
    Linnaeus
    -0.33
    POSITIVE LOGITS
     "..\..\
    0.83
     "..\..\..\
    0.82
    MessageTagHelper
    0.77
     للمعارف
    0.76
    __(/*!
    0.71
    клопе
    0.71
    archiviato
    0.70
    Tikang
    0.70
     lest
    0.69
    собенности
    0.68
    Activations Density 0.568%

    No Known Activations