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-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 23987
    Prev
    Next
    INDEX
    Explanations

    terms related to technical components and their configurations in engineering contexts

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

    geometric shapes and physical components

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    either
    -0.40
     either
    -0.38
     to
    -0.37
     ninguém
    -0.37
    kolwiek
    -0.35
    yn
    -0.35
     not
    -0.35
     pokok
    -0.35
     tendrás
    -0.34
     yalnızca
    -0.34
    POSITIVE LOGITS
     surla
    0.78
    :✨
    0.67
    LookAnd
    0.65
    ỡng
    0.64
     pleaſure
    0.58
    postsleuth
    0.58
     betweenstory
    0.57
    󠁮
    0.57
    nodoc
    0.56
    setVerticalGroup
    0.56
    Activations Density 0.457%

    No Known Activations