© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 39-GEMMASCOPE-RES-16K
    11. 2616
    Prev
    Next
    INDEX
    Explanations

    statements and phrases indicating intent or plans for future actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.39.hook_resid_post
    Hook Layer
    39
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     iconLine
    -0.52
    batore
    -0.50
     հղումներ
    -0.49
    ználat
    -0.45
    DebuggerNonUser
    -0.44
    UrlResolution
    -0.44
    :✨
    -0.43
     autorytatywna
    -0.43
     saites
    -0.41
    Erstellt
    -0.41
    POSITIVE LOGITS
     plan
    2.39
     plans
    2.39
     intend
    2.17
     intends
    2.06
    plans
    1.95
    plan
    1.92
    Plans
    1.91
     Plans
    1.89
     intention
    1.86
     PLANS
    1.78
    Activations Density 0.635%

    No Known Activations