© 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. 20-GEMMASCOPE-RES-16K
    11. 12024
    Prev
    Next
    INDEX
    Explanations

    descriptive elements related to terrain and inclines in a hiking or driving context

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

    slopes and inclines

    np_acts-logits-general · gemini-2.0-flash

    steep inclines and slopes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MessageOf
    -0.67
    出版年
    -0.65
    afficheront
    -0.63
     nahilalakip
    -0.62
     Infórmanos
    -0.62
    lankton
    -0.57
    insics
    -0.57
    qtype
    -0.54
     referenties
    -0.53
    mobileqq
    -0.53
    POSITIVE LOGITS
     slope
    1.71
     steep
    1.62
     slopes
    1.61
     hill
    1.44
     steeper
    1.43
     Slope
    1.41
     hills
    1.36
    slope
    1.35
     downhill
    1.34
     sloping
    1.33
    Activations Density 0.316%

    No Known Activations