© 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. 21-GEMMASCOPE-RES-16K
    11. 2137
    Prev
    Next
    INDEX
    Explanations

    phrases indicating conditionality, obligation, or potentiality in actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mourut
    -0.91
     étoit
    -0.76
     auroit
    -0.73
     disfrutando
    -0.71
     avoient
    -0.70
     giudi
    -0.69
     financière
    -0.67
     pidiendo
    -0.66
     venait
    -0.65
     preparando
    -0.64
    POSITIVE LOGITS
     take
    1.58
     make
    1.58
     be
    1.54
     get
    1.49
     create
    1.42
     become
    1.42
     give
    1.38
     go
    1.38
     come
    1.33
     develop
    1.32
    Activations Density 3.302%

    No Known Activations