© 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 EvalsExportsinterp-engineNEWAPI 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. 904
    Prev
    Next
    INDEX
    Explanations

    instances of uncertainty or ambiguity

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

    following "somehow" or "some"

    np_acts-logits-general · gemini-2.0-flash

    somehow, some reason, some form

    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
     massima
    -0.36
     rétro
    -0.34
     umum
    -0.31
     keselamatan
    -0.31
    heureusement
    -0.31
     palju
    -0.30
    เฉ
    -0.30
     paljon
    -0.29
     expuesto
    -0.29
     perspectiva
    -0.28
    POSITIVE LOGITS
     somehow
    1.44
     Somehow
    1.41
    Somehow
    1.33
    somewhere
    1.21
     somewhere
    1.21
     Somewhere
    1.20
    Somewhere
    1.16
    something
    1.03
     Something
    1.02
     someplace
    1.02
    Activations Density 0.468%

    No Known Activations