© 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. 1707
    Prev
    Next
    INDEX
    Explanations

    references to measurements and physical properties related to motion and stability in a scientific context

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

    Direction or orientation

    np_acts-logits-general · gemini-2.0-flash

    spatial direction and orientation

    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
    +:+
    -0.50
    Personensuche
    -0.49
     elite
    -0.45
     '~
    -0.45
     mark
    -0.45
     mou
    -0.45
     cache
    -0.45
    astify
    -0.44
    thumb
    -0.44
     thumb
    -0.43
    POSITIVE LOGITS
     vertically
    0.84
     perpendicular
    0.78
     vertical
    0.78
     lengthwise
    0.74
     verticale
    0.74
     horizontally
    0.72
     orthogonal
    0.71
     horizontal
    0.70
     axis
    0.69
    Vertical
    0.69
    Activations Density 0.926%

    No Known Activations