© 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. 11304
    Prev
    Next
    INDEX
    Explanations

    words related to physical dimensions and spatial orientation

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

    Rotation around an axis

    np_acts-logits-general · gemini-2.0-flash

    parallel and perpendicular axes

    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
    Gemeinden
    -0.55
    InitVars
    -0.46
     löst
    -0.44
     HttpServlet
    -0.43
     bellows
    -0.42
     Wrang
    -0.42
    styleUrls
    -0.42
     Yü
    -0.41
    itonitis
    -0.41
    页面存档备份
    -0.41
    POSITIVE LOGITS
     perpendicular
    1.27
     parallel
    1.15
     axis
    1.09
    parallel
    0.98
     parallelism
    0.98
     Parallel
    0.98
     line
    0.96
    pendicular
    0.95
     axes
    0.93
     tangent
    0.93
    Activations Density 0.598%

    No Known Activations