© 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. 1535
    Prev
    Next
    INDEX
    Explanations

    numerical scores, leads, and point differences in competitive contexts

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

    numerical sports statistics and scoring details.

    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
     Administrativna
    -0.80
     Reverso
    -0.61
     autorytatywna
    -0.58
    OGND
    -0.57
     Doors
    -0.56
    RTLI
    -0.54
     CanadaChoose
    -0.52
    rifuge
    -0.50
     doors
    -0.49
     Caster
    -0.49
    POSITIVE LOGITS
     AssemblyVersion
    0.46
     invokingState
    0.38
    testens
    0.33
    IntoConstraints
    0.32
     întâ
    0.30
     arasındaki
    0.29
     anfangs
    0.29
     թ
    0.28
    ellees
    0.27
     aplic
    0.27
    Activations Density 0.039%

    No Known Activations