© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 3873
    Prev
    Next
    INDEX
    Explanations

    patterns of data related to specific programming or coding elements

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

    hexadecimal or memory address-related syntax in programming code.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    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
    campista
    -0.29
     OMITBAD
    -0.27
    fjspx
    -0.26
    Források
    -0.23
     faute
    -0.23
    fahrer
    -0.22
     fares
    -0.22
    لق
    -0.22
     what
    -0.22
     filles
    -0.21
    POSITIVE LOGITS
     HasFactory
    0.74
    ⪜
    0.69
     queſta
    0.68
     $_(
    0.63
    openzeppelin
    0.61
     okuyayım
    0.61
     vermogen
    0.61
    wapV
    0.60
     userDao
    0.60
    bootstrapcdn
    0.60
    Activations Density 0.010%

    No Known Activations