© 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. 18-GEMMASCOPE-RES-16K
    11. 2881
    Prev
    Next
    INDEX
    Explanations

    text describing physical or mechanical properties and functionalities, particularly in relation to sports equipment and performance

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

    Shock absorption and collision

    np_acts-logits-general · gemini-2.0-flash

    shock absorber

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Normdatei
    -0.65
    kette
    -0.60
    Демографія
    -0.58
    </tfoot>
    -0.55
    seth
    -0.54
    riez
    -0.54
    qrstuvwxyz
    -0.54
    uterie
    -0.52
     rối
    -0.51
    èche
    -0.51
    POSITIVE LOGITS
     impact
    1.10
    impact
    0.99
     shock
    0.98
     collision
    0.94
     Impact
    0.93
     удар
    0.91
    Impact
    0.91
     impacts
    0.90
     hits
    0.90
     collisions
    0.88
    Activations Density 0.214%

    No Known Activations