© 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. 10-GEMMASCOPE-RES-16K
    11. 9361
    Prev
    Next
    INDEX
    Explanations

    intensifiers and qualifiers used to emphasize specific conditions or situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Spoljašnje
    -0.44
    PullParser
    -0.44
     للمعارف
    -0.43
     Haush
    -0.40
     Kelly
    -0.40
    alay
    -0.38
    ragt
    -0.37
    Legături
    -0.36
     adult
    -0.36
    uksi
    -0.36
    POSITIVE LOGITS
     noDo
    0.59
     nahilalakip
    0.46
    ValueStyle
    0.46
    GOTREF
    0.45
    gebob
    0.44
    QMetaType
    0.43
    TypedDataSet
    0.43
     Autorisations
    0.43
     transfieras
    0.42
    icitis
    0.42
    Activations Density 0.903%

    No Known Activations