© 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-2-2B
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 1180
    Prev
    Next
    INDEX
    Explanations

    expressions related to permission or enabling actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/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.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    YNC
    -0.82
     StatelessWidget
    -0.74
     než
    -0.71
     bains
    -0.70
     demais
    -0.69
    SessionFactory
    -0.68
     fatica
    -0.68
     démission
    -0.67
    »?
    -0.67
     cister
    -0.66
    POSITIVE LOGITS
     ALLOW
    1.56
    ALLOW
    1.52
     Allow
    1.47
     allow
    1.41
     allows
    1.40
     Allows
    1.39
     allowed
    1.37
    Allows
    1.32
    Allow
    1.31
     allowing
    1.30
    Activations Density 0.121%

    No Known Activations