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. 103215
    Prev
    Next
    INDEX
    Explanations

    mathematical and programming-related symbols or terms

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

    Whitespace tokens and small connecting words that serve as structural elements in technical documents, code, and formatted data.

    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
     nahilalakip
    -0.47
    FindBy
    -0.34
    MockMvc
    -0.33
    ########.
    -0.33
    świad
    -0.33
     Ne
    -0.32
    ofd
    -0.32
     Unmarshal
    -0.32
    //
    -0.32
    fr
    -0.32
    POSITIVE LOGITS
    Personendaten
    0.75
    SharedCtor
    0.63
    LookAnd
    0.59
    queryInterface
    0.59
    httphttps
    0.56
    XmlEnum
    0.52
     OMITBAD
    0.52
    DrawerToggle
    0.52
    értel
    0.49
    webElementXpaths
    0.48
    Activations Density 0.195%

    No Known Activations