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. 4-GEMMASCOPE-RES-16K
    6. 11985
    Prev
    Next
    INDEX
    Explanations

    C programming language data types and structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enderror
    -0.67
    ImageIO
    -0.64
    ContentAsync
    -0.63
    ConverterFactory
    -0.59
    requestCode
    -0.57
    ArgsConstructor
    -0.56
    Smarty
    -0.56
    
    -0.54
    routeProvider
    -0.50
    theless
    -0.50
    POSITIVE LOGITS
    getLong
    0.73
    setLong
    0.71
    bigint
    0.66
    long
    0.66
     long
    0.65
     ulong
    0.64
     DWORD
    0.63
     BigInt
    0.63
    mybatisplus
    0.62
    UINTN
    0.59
    Activations Density 0.422%

    No Known Activations