© 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. 16-GEMMASCOPE-RES-16K
    11. 11980
    Prev
    Next
    INDEX
    Explanations

    terms related to qualitative analysis and measurements in scientific contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_16/width_16k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kal
    -0.32
     drawing
    -0.31
     kom
    -0.31
     Künst
    -0.31
     Kal
    -0.31
    Drawing
    -0.30
     gj
    -0.30
    ross
    -0.29
    言うと
    -0.29
     diverting
    -0.28
    POSITIVE LOGITS
    GOTREF
    0.68
    jsxFileName
    0.66
     queſta
    0.65
    parsedMessage
    0.65
    MessageTagHelper
    0.62
    mergeFrom
    0.60
    providedIn
    0.60
     BitmapFactory
    0.59
    WriteBarrier
    0.59
     ſte
    0.58
    Activations Density 1.724%

    No Known Activations