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. 24-GEMMASCOPE-RES-16K
    6. 12719
    Prev
    Next
    INDEX
    Explanations

    references to methods and functions in programming, particularly related to date and time manipulation

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

    Java method calls

    np_acts-logits-general · gemini-2.0-flash

    java method calls

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 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
     препратки
    -0.77
    rungsseite
    -0.72
    Климат
    -0.67
    Datuak
    -0.65
    SharedCtor
    -0.62
    انجليز
    -0.60
    esez
    -0.58
    קישורים
    -0.58
     vuitton
    -0.58
    ^(@
    -0.55
    POSITIVE LOGITS
    hashCode
    0.57
    toString
    0.54
    LLocation
    0.50
    getClass
    0.49
     naturelles
    0.47
    amples
    0.46
     hashCode
    0.46
     inwoners
    0.46
    VersionUID
    0.46
    randomUUID
    0.45
    Activations Density 0.087%

    No Known Activations