© 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-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 10898
    Prev
    Next
    INDEX
    Explanations

    instances of assistance or involvement in collaborative efforts

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

    Infinitive form of verbs

    np_acts-logits-general · gemini-2.0-flash

    decide and do

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BeginContext
    -0.93
     saites
    -0.62
    IBAction
    -0.58
     rosse
    -0.55
     femmin
    -0.54
    MigrationBuilder
    -0.54
    tagHelperRunner
    -0.53
     indépendant
    -0.53
    PDOException
    -0.52
    adaptiveStyles
    -0.52
    POSITIVE LOGITS
     decide
    1.42
     figure
    1.36
     deciding
    1.25
     Decide
    1.20
     devise
    1.16
    decide
    1.16
    Decide
    1.15
     determine
    1.15
    figure
    1.15
     decides
    1.14
    Activations Density 0.389%

    No Known Activations