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-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 14913
    Prev
    Next
    INDEX
    Explanations

    keywords and expressions related to object initialization in programming

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

    Code-related terms and symbols

    np_acts-logits-general · gemini-2.0-flash

    code delimiters and structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     незавершена
    -0.50
    ThroughAttribute
    -0.41
     skj
    -0.39
     tilbage
    -0.38
     nemlig
    -0.36
     AspNetCore
    -0.35
     freshest
    -0.35
    뀐
    -0.35
     محفوظة
    -0.35
     fleste
    -0.34
    POSITIVE LOGITS
    SharedDtor
    0.70
    __()
    0.69
    didSet
    0.67
    CastException
    0.55
    ftagPool
    0.53
    HtmlAttribute
    0.52
    SharedCtor
    0.51
    UseVisualStyle
    0.49
     createState
    0.49
    nodoc
    0.47
    Activations Density 0.031%

    No Known Activations