© 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. 16-GEMMASCOPE-RES-16K
    11. 1248
    Prev
    Next
    INDEX
    Explanations

    terms related to light, visibility, and transparency issues

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

    Signals undesirable consequences

    np_acts-logits-general · gemini-2.0-flash

    increases costs and problems

    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
    HasAnnotation
    -0.59
     grâce
    -0.52
    httphttps
    -0.51
    RTN
    -0.51
    queryInterface
    -0.50
    ArgumentParser
    -0.50
    grazie
    -0.50
    ificent
    -0.49
     McClure
    -0.48
    IsMutable
    -0.48
    POSITIVE LOGITS
     unavoidable
    0.84
    Worse
    0.79
     Worse
    0.78
     unavoid
    0.77
     unnecessarily
    0.75
     uncontrol
    0.69
     worse
    0.68
     exacerb
    0.67
     demais
    0.67
     unduly
    0.67
    Activations Density 1.023%

    No Known Activations