© 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. 2544
    Prev
    Next
    INDEX
    Explanations

    references to "ball" and its related terms or contexts

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

    following "ball"

    np_acts-logits-general · gemini-2.0-flash

    words containing "ball" or starting with "Bal"

    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
    Recu
    -0.70
     rejo
    -0.60
     dentists
    -0.58
    ecan
    -0.55
    glades
    -0.54
     الإسلامية
    -0.54
     Recu
    -0.54
     Shady
    -0.53
     صوتيه
    -0.53
    webe
    -0.53
    POSITIVE LOGITS
     BALL
    1.18
     Ball
    1.11
    Ball
    1.07
     ball
    1.06
     balls
    1.06
    Balls
    1.04
     Balls
    0.99
    ball
    0.96
     Baller
    0.94
    BALL
    0.93
    Activations Density 0.126%

    No Known Activations