© 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. 14-GEMMASCOPE-RES-16K
    11. 7343
    Prev
    Next
    INDEX
    Explanations

    elements related to games and gameplay mechanics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     avoient
    -0.74
     feroit
    -0.73
     chré
    -0.70
     Grecs
    -0.69
     ainfi
    -0.68
     Romains
    -0.67
     devenus
    -0.67
     supérieures
    -0.67
     étoient
    -0.65
     raiſ
    -0.64
    POSITIVE LOGITS
     كومونز
    0.63
     missions
    0.58
    /**/*.
    0.55
     player
    0.55
    providedIn
    0.55
    ViewChild
    0.53
     press
    0.51
     familiar
    0.50
    Биография
    0.50
     /\.(
    0.48
    Activations Density 0.159%

    No Known Activations