© 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. 24-GEMMASCOPE-RES-16K
    11. 13742
    Prev
    Next
    INDEX
    Explanations

    phrases related to data analysis and performance metrics

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

    Comparison or exceeding expectations

    np_acts-logits-general · gemini-2.0-flash

    exceeds surpasses outweighs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dAtA
    -0.58
    FunctionFlags
    -0.56
    delwed
    -0.53
     Winaray
    -0.53
     useCallback
    -0.52
    akterysty
    -0.50
    خصة
    -0.49
    RenderAtEndOf
    -0.49
    Enllaces
    -0.49
    rungsseite
    -0.46
    POSITIVE LOGITS
     surpass
    1.79
     surpassed
    1.74
     beat
    1.69
     surpasses
    1.66
     surpassing
    1.55
     beats
    1.54
     exceed
    1.50
     exceeded
    1.45
     exceeds
    1.44
     beating
    1.37
    Activations Density 0.497%

    No Known Activations