© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 102560
    Prev
    Next
    INDEX
    Explanations

    references to television shows and personal projects

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

    Common terminators (periods, punctuation) and conjunctions that connect text segments, often appearing at the end of descriptions of personal activities, projects, or time references.

    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
    OGND
    -0.50
    ---*/
    -0.44
    }{*}{}
    -0.43
    Gambas
    -0.42
     $_"
    -0.42
    SharedDtor
    -0.41
     stru
    -0.41
     صوتيه
    -0.41
     ture
    -0.40
    exo
    -0.40
    POSITIVE LOGITS
     Menschheit
    0.49
     titulada
    0.45
    sproz
    0.44
    getSupport
    0.43
    Dimensões
    0.42
     Audiodateien
    0.42
     našich
    0.41
     partij
    0.41
     vieilles
    0.40
     varones
    0.40
    Activations Density 0.102%

    No Known Activations