© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 105527
    Prev
    Next
    INDEX
    Explanations

    terms related to data assessment and evaluation methods

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    Noun phrases and prepositional phrases that connect or specify relationships between technical concepts, particularly in academic, legal, or technical writing.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219
    Triggered 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
    Negative Logits
    migrationBuilder
    -0.66
     оригіналу
    -0.64
    XmlRootElement
    -0.48
    bootstrapcdn
    -0.45
    enderror
    -0.45
     OMITBAD
    -0.44
     trie
    -0.44
     Audiodateien
    -0.44
     IBOutlet
    -0.42
    principalTable
    -0.42
    POSITIVE LOGITS
    tvguidetime
    0.49
    ⓧ
    0.48
    LookAnd
    0.39
     Upon
    0.34
    Upon
    0.34
    ubahan
    0.31
    afficheront
    0.31
    ască
    0.31
     esperti
    0.31
     informiert
    0.30
    Activations Density 0.060%

    No Known Activations