© 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. 12483
    Prev
    Next
    INDEX
    Explanations

    references to data fitting techniques and analysis methods in scientific contexts

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

    Arrows, lines, and shapes in diagrams

    np_acts-logits-general · gemini-2.0-flash

    dashed lines and arrows

    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
    mybatisplus
    -0.59
     säll
    -0.59
    LikeLiked
    -0.57
    matchCondition
    -0.54
    исленность
    -0.53
     AssemblyTitle
    -0.53
     hanem
    -0.53
     AspNetCore
    -0.52
     MaterialApp
    -0.52
    DialogContent
    -0.50
    POSITIVE LOGITS
     dashed
    1.22
     arrows
    1.17
     dotted
    1.09
     shaded
    1.03
     arrow
    1.03
     circles
    1.01
    dashed
    0.98
     solid
    0.98
     dots
    0.96
     hatched
    0.94
    Activations Density 1.364%

    No Known Activations