© 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. 31-GEMMASCOPE-RES-16K
    11. 3295
    Prev
    Next
    INDEX
    Explanations

    evaluative language regarding recommendations and assessments

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

    words and phrases that convey strong positive recommendations or endorsements.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/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.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     <<<<<<<<<<<<<<
    -0.46
     JADX
    -0.43
    那样
    -0.42
    addContainerGap
    -0.38
     öyle
    -0.36
    NameInMap
    -0.34
    postIndex
    -0.34
     Оно
    -0.33
    ⓧ
    -0.32
    eningrad
    -0.30
    POSITIVE LOGITS
     this
    3.09
     này
    1.92
     denna
    1.91
     această
    1.88
    this
    1.87
     tämä
    1.87
     acest
    1.83
     этого
    1.82
     dieser
    1.81
     questa
    1.78
    Activations Density 5.328%

    No Known Activations