© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 9357
    Prev
    Next
    INDEX
    Explanations

    terms related to assessments and evaluations

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

    "assessment" or "assess"

    np_acts-logits-general · gemini-2.0-flash

    assessment of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     klikken
    -0.66
     operação
    -0.53
     éditoriale
    -0.53
     operações
    -0.52
     operazioni
    -0.49
     financières
    -0.48
    zarchiwizowane
    -0.48
     Valenzuela
    -0.48
     rumor
    -0.48
     Emig
    -0.48
    POSITIVE LOGITS
     Assessment
    1.38
     assessment
    1.36
    Assessment
    1.32
    assessment
    1.30
     ASSESSMENT
    1.24
    Assess
    1.23
     assessments
    1.21
    assess
    1.20
     assess
    1.20
    ASSESSMENT
    1.19
    Activations Density 0.179%

    No Known Activations