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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 8152
    Prev
    Next
    INDEX
    Explanations

    terms related to classification and evaluation in scientific contexts

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

    verbs that describe processes, actions, or states occurring in academic or technical contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     itself
    -0.70
     its
    -0.67
     Its
    -0.58
     яке
    -0.56
    Its
    -0.56
    itself
    -0.54
     которое
    -0.51
     său
    -0.50
    它的
    -0.50
    its
    -0.48
    POSITIVE LOGITS
     themselves
    1.04
    themselves
    0.94
     amelyek
    0.75
     jotka
    0.69
     которые
    0.69
     eivät
    0.66
     generalizations
    0.64
     nejsou
    0.64
     cherchés
    0.64
     abstractions
    0.63
    Activations Density 1.956%

    No Known Activations