Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 86073
    Prev
    Next
    INDEX
    Explanations

    references to patients and species in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    medical patients or biological species

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ItemBackground
    -0.59
    InjectAttribute
    -0.57
    TRAILING
    -0.56
    estacks
    -0.53
    dflare
    -0.52
    InputBorder
    -0.51
    TypedDataSet
    -0.50
    fromnode
    -0.49
    uvwxyz
    -0.49
    cloudflare
    -0.48
    POSITIVE LOGITS
    rungsseite
    0.49
    chieht
    0.38
     keskus
    0.35
    clearInterval
    0.35
     inš
    0.34
    consulté
    0.34
    lanniksi
    0.33
    Litteratur
    0.33
     Bupati
    0.32
     henkil
    0.32
    Activations Density 0.128%

    No Known Activations