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. 122956
    Prev
    Next
    INDEX
    Explanations

    comments or markers within a code or text structure

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

    Discourse markers and transitional phrases that signal a shift in topic, introduce a conclusion, or connect different sections of text.

    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
    inSlope
    -0.52
    الحياه
    -0.48
     незавершена
    -0.46
    Personendaten
    -0.45
    SequentialGroup
    -0.45
    dibu
    -0.45
     Roskov
    -0.45
    RTSN
    -0.43
     disambiguazione
    -0.43
    noble
    -0.43
    POSITIVE LOGITS
     then
    0.48
    AccessorTable
    0.45
    さて
    0.42
     digress
    0.41
     THEN
    0.39
     thus
    0.39
     Then
    0.38
    KURZBESCHREIBUNG
    0.38
     sitten
    0.38
     yeah
    0.38
    Activations Density 0.063%

    No Known Activations