© 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. 9-GEMMASCOPE-RES-16K
    6. 1120
    Prev
    Next
    INDEX
    Explanations

    terms associated with worship practices and rituals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    batore
    -0.63
    ContentAlignment
    -0.62
    uterte
    -0.60
    wahati
    -0.59
    seus
    -0.58
     pax
    -0.56
     IPR
    -0.56
     Penang
    -0.55
     Prudence
    -0.54
     synergies
    -0.53
    POSITIVE LOGITS
    bukkit
    0.68
    GenerationType
    0.60
     complètes
    0.60
    berdayakan
    0.60
    URLException
    0.56
     wajah
    0.55
    :+:
    0.55
    setLayoutManager
    0.54
    Affiliation
    0.53
    detectChanges
    0.52
    Activations Density 0.034%

    No Known Activations