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

    Neuronpedia

    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. 25-GEMMASCOPE-RES-16K
    11. 15834
    Prev
    Next
    INDEX
    Explanations

    phrases that express purpose or justification for actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_25/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.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rungsseite
    -0.73
     GenerationType
    -0.67
    AsUp
    -0.60
    MemoryWarning
    -0.59
     فريبيس
    -0.59
     configureStore
    -0.56
     Zig
    -0.55
     nahilalakip
    -0.54
    contentLoaded
    -0.54
    ロウィン
    -0.53
    POSITIVE LOGITS
     sake
    0.58
     purposes
    0.50
    findpost
    0.49
     Zwecke
    0.44
     kepentingan
    0.43
     Erhaltung
    0.42
     أجل
    0.42
     aşk
    0.41
     purpose
    0.40
     reasons
    0.40
    Activations Density 0.238%

    No Known Activations