© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 14544
    Prev
    Next
    INDEX
    Explanations

    references to figures and data visualizations in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "Fig" followed by a period or bracket

    np_acts-logits-general · gemini-2.0-flash

    fig references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AsUp
    -0.79
    ItemBackground
    -0.66
     ?>/
    -0.65
     发表于
    -0.63
    _
    
    -0.61
     {}));
    -0.61
    mybatisplus
    -0.61
    istert
    -0.60
    WebElementEntity
    -0.59
    >*/
    -0.58
    POSITIVE LOGITS
    Fig
    0.84
     Fig
    0.77
    Figure
    0.73
    IBOutlet
    0.73
     Figure
    0.60
    setVerticalGroup
    0.56
     InputDecoration
    0.55
     الحره
    0.53
     Figs
    0.53
     Driver
    0.51
    Activations Density 0.284%

    No Known Activations