© 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. 3893
    Prev
    Next
    INDEX
    Explanations

    statistical relationships and comparisons in research data

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

    Sentences ending with a period (.)

    np_acts-logits-general · gemini-2.0-flash

    conclusions and implications

    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
    WebVitals
    -0.69
    enumi
    -0.66
    ChildScrollView
    -0.65
    TypedDataSet
    -0.62
    LocationManager
    -0.61
    extAlignment
    -0.61
    andaag
    -0.59
     defaultstate
    -0.59
     ControllerBase
    -0.59
     recensement
    -0.59
    POSITIVE LOGITS
    Conclusions
    0.73
    Conclusion
    0.73
    Conversely
    0.70
     Conversely
    0.66
     conclusion
    0.65
    Implications
    0.65
    CONCLUSIONS
    0.64
     Interestingly
    0.64
    Interestingly
    0.63
     implication
    0.60
    Activations Density 1.292%

    No Known Activations