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. 13029
    Prev
    Next
    INDEX
    Explanations

    specific values and types in a programming context, particularly regarding object attributes and function definitions

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

    Code containing "0.0f"

    np_acts-logits-general · gemini-2.0-flash

    float literals and floating point numbers

    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
    mybatisplus
    -0.94
     مشين
    -0.94
    setVerticalGroup
    -0.80
     Efq
    -0.78
    SourceChecksum
    -0.77
    contentLoaded
    -0.76
    دانشنامهٔ
    -0.75
    Datuak
    -0.74
    DockStyle
    -0.73
    >");
    
    -0.70
    POSITIVE LOGITS
    vece
    0.46
    f
    0.42
    担当
    0.39
     NSObject
    0.39
     double
    0.39
    が取
    0.38
    TestBase
    0.38
    を取
    0.38
    ieuse
    0.37
    COE
    0.37
    Activations Density 0.183%

    No Known Activations