© 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. 33-GEMMASCOPE-RES-16K
    11. 11098
    Prev
    Next
    INDEX
    Explanations

    actions and plans related to personal safety and household management

    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
     wedstrijd
    -0.42
    canestro
    -0.42
    現地
    -0.41
     hemel
    -0.40
     jurí
    -0.39
     agrícolas
    -0.39
    vip
    -0.36
    ril
    -0.35
     beroep
    -0.35
    VIP
    -0.35
    POSITIVE LOGITS
     downstairs
    1.32
     upstairs
    1.30
     room
    1.20
     bedroom
    1.19
     rooms
    1.18
     bedrooms
    1.09
     Room
    1.05
     kitchen
    1.05
    room
    0.98
     ROOM
    0.98
    Activations Density 0.514%

    No Known Activations