Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 214
    Prev
    Next
    INDEX
    Explanations

    comments and documentation in code

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

    programming language syntax, particularly focusing on class, function, and method definitions.

    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
    AndEndTag
    -0.65
     Normdatei
    -0.61
    rungsseite
    -0.59
     كومونز
    -0.59
     فريبيس
    -0.58
     SDLK
    -0.57
     BoxFit
    -0.56
     betweenstory
    -0.54
    Portail
    -0.52
     propTypes
    -0.52
    POSITIVE LOGITS
    Parts
    0.40
     gens
    0.37
     parts
    0.36
     Parts
    0.35
    い
    0.34
    struct
    0.33
     tribu
    0.33
     _
    0.33
    bu
    0.33
    ↵
    0.33
    Activations Density 0.092%

    No Known Activations