© 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
    7. Residual Stream - 16k
    9. 33-GEMMASCOPE-RES-16K
    11. 13902
    Prev
    Next
    INDEX
    Explanations

    expressions of recommendation and endorsement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SourceChecksum
    -0.41
    fillType
    -0.40
    StoryboardSegue
    -0.34
    HXLINE
    -0.33
    TagMode
    -0.33
    AnimationsModule
    -0.33
    textAppearance
    -0.33
    ც
    -0.31
    вость
    -0.30
    MockMvc
    -0.29
    POSITIVE LOGITS
     recommendation
    3.50
     recommended
    3.39
     recommend
    3.31
     recommendations
    3.28
     recommending
    3.09
     recommends
    3.09
     Recommendation
    2.97
    recommended
    2.91
     Recommendations
    2.91
     recomend
    2.86
    Activations Density 0.980%

    No Known Activations