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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 7923
    Prev
    Next
    INDEX
    Explanations

    business-related terms and phrases related to company operations and promotions

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

    Word after "of," "at," or "is"

    np_acts-logits-general · gemini-2.0-flash

    verbs often followed by entities

    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
     Anſ
    -1.23
     itſelf
    -1.20
     Efq
    -1.17
     Houſe
    -1.16
     ―――――
    -1.16
     Reſ
    -1.14
     Eſ
    -1.13
     ་་
    -1.12
     Diſ
    -1.10
     Majefty
    -1.10
    POSITIVE LOGITS
     K
    0.90
     V
    0.85
     F
    0.85
     The
    0.85
     Z
    0.85
     J
    0.83
     G
    0.82
     D
    0.80
     H
    0.80
     B
    0.79
    Activations Density 0.959%

    No Known Activations