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. 12602
    Prev
    Next
    INDEX
    Explanations

    special characters and formatting in a document

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

    Code, paths, or filenames

    np_acts-logits-general · gemini-2.0-flash

    technical terms and programming code

    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
    <strong>
    -0.54
    <em>
    -0.53
    <i>
    -0.50
    1
    -0.46
    <b>
    -0.45
    <u>
    -0.45
    وانید
    -0.43
    2
    -0.43
    Cancelled
    -0.43
    あくまで
    -0.43
    POSITIVE LOGITS
     فريبيس
    0.92
     <=",
    0.90
    Personensuche
    0.85
     Meksiku
    0.81
    Personendaten
    0.78
    IndentedString
    0.77
    addCriterion
    0.76
     Wicidata
    0.76
    LookAnd
    0.74
    ThroughAttribute
    0.73
    Activations Density 0.396%

    No Known Activations