© 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. 6208
    Prev
    Next
    INDEX
    Explanations

    assessments of reasonableness in various contexts

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

    "reasonable"

    np_acts-logits-general · gemini-2.0-flash

    reasonableness and related judgments

    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
    deselect
    -0.36
     raw
    -0.36
     getInfo
    -0.35
     swojego
    -0.34
    tss
    -0.33
     exactement
    -0.32
    langsung
    -0.31
     MINES
    -0.31
     mengirimkan
    -0.31
     gelijk
    -0.31
    POSITIVE LOGITS
    reasonable
    1.40
     reasonable
    1.39
    Reasonable
    1.38
     Reasonable
    1.38
     reasonableness
    1.24
     realistic
    1.15
     Realistic
    1.13
    realistic
    1.10
    Realistic
    1.10
     raisonnable
    1.05
    Activations Density 0.347%

    No Known Activations