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
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 1193
    Prev
    Next
    INDEX
    Explanations

    scientific and technical terms related to processes in molecular biology and biochemistry

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

    [Word] of [something]

    np_acts-logits-general · gemini-2.0-flash

    processes and their outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     חיצוניים
    -0.59
     newUser
    -0.55
     Defenders
    -0.52
     Deuter
    -0.49
     NSCoder
    -0.49
    MigrationBuilder
    -0.48
     فريبيس
    -0.48
    miller
    -0.47
    orithmic
    -0.47
    mobileqq
    -0.47
    POSITIVE LOGITS
     of
    0.47
    ennung
    0.46
    folgung
    0.42
     Ouverture
    0.41
    Aholisi
    0.41
     certain
    0.39
    stination
    0.38
    ACJA
    0.36
     utilization
    0.36
     purposes
    0.36
    Activations Density 1.119%

    No Known Activations