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 - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 117319
    Prev
    Next
    INDEX
    Explanations

    mathematical concepts and notations related to equations and relationships

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

    Technical or academic text describing standards, supported formats, or theoretical/reference elements that serve as comparative benchmarks in documentation, scientific writing, or formal notation.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
    Hentet
    -0.54
     surla
    -0.37
    LabelTagHelper
    -0.36
    icoot
    -0.35
     Normdatei
    -0.35
    pox
    -0.35
     للاسماء
    -0.35
     Hentet
    -0.35
    iredo
    -0.34
    nexo
    -0.34
    POSITIVE LOGITS
    GTCX
    0.54
     Wicidata
    0.44
    XmlAccessType
    0.43
     برانيه
    0.43
     antworte
    0.42
     Audiodateien
    0.41
     poffible
    0.41
    webElementGuid
    0.41
     thiệu
    0.40
    Sklici
    0.40
    Activations Density 0.238%

    No Known Activations