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-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 13055
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate the significance or crucial role of certain entities or concepts

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

    "role" after the word "play" or "a"

    np_acts-logits-general · gemini-2.0-flash

    play a role

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ThroughAttribute
    -0.65
    bcryptjs
    -0.64
     مشين
    -0.59
     ©️
    -0.58
    Халык
    -0.53
    ViewImports
    -0.53
    dziew
    -0.52
    Попис
    -0.50
     Kette
    -0.50
    GraphicsUnit
    -0.49
    POSITIVE LOGITS
     role
    2.38
    role
    1.96
     roles
    1.90
     Role
    1.85
    Role
    1.81
     rôle
    1.75
     ROLE
    1.70
     ruolo
    1.59
     rôles
    1.55
     Roles
    1.55
    Activations Density 0.255%

    No Known Activations