© 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. 2-GEMMASCOPE-RES-16K
    11. 779
    Prev
    Next
    INDEX
    Explanations

    phrases indicating actions and events related to decision-making and responsibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ontvang
    -0.52
    opsida
    -0.47
    InitVars
    -0.46
    ValueGenerated
    -0.45
     znaczy
    -0.42
    (||
    -0.41
     utafitiHapana
    -0.41
     lenker
    -0.41
    ‌است
    -0.40
     Italijani
    -0.40
    POSITIVE LOGITS
    enumi
    0.87
    帖最后由
    0.86
    
    0.74
    Hozzáférés
    0.70
    LayoutConstraint
    0.69
    fastjson
    0.68
    tagHelperRunner
    0.68
     ſtand
    0.67
    GEBURTSDATUM
    0.66
    extAlignment
    0.65
    Activations Density 0.789%

    No Known Activations