© 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. 3003
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to evidence and validity in arguments or claims

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

    numerical and statistical language related to research, evidence, and measurement.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered 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
    .
    -0.42
     satunya
    -0.30
    開心
    -0.25
     paraître
    -0.24
     things
    -0.24
    突
    -0.24
     include
    -0.24
    attach
    -0.24
    成
    -0.24
     kuulu
    -0.23
    POSITIVE LOGITS
     ſind
    0.91
    CloseOperation
    0.81
     ſei
    0.73
     zwiſchen
    0.68
     ſont
    0.67
    ￪
    0.66
     ſehr
    0.66
    aarrggbb
    0.66
     ſich
    0.66
     auffi
    0.66
    Activations Density 0.525%

    No Known Activations