© 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
    7. Residual Stream - 16k
    9. 0-GEMMASCOPE-RES-16K
    11. 14207
    Prev
    Next
    INDEX
    Explanations

    expressions of uncertainty or speculation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     lenker
    -0.62
     IBOutlet
    -0.58
     houſe
    -0.57
    oa̍t
    -0.56
    PerformLayout
    -0.55
    enderror
    -0.55
    TypedDataSet
    -0.54
    VersionUID
    -0.54
    niająca
    -0.53
    UnusedPrivate
    -0.52
    POSITIVE LOGITS
     probably
    3.30
     presumably
    3.22
     perhaps
    3.05
    probably
    3.02
    presumably
    2.88
    Probably
    2.86
     Probably
    2.84
     possibly
    2.80
     Presumably
    2.78
     probablemente
    2.77
    Activations Density 0.269%

    No Known Activations