© 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. 24-GEMMASCOPE-RES-16K
    11. 8563
    Prev
    Next
    INDEX
    Explanations

    references to engineering concepts related to phase relationships in motors

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

    the concept of "reverse" or "reversed"

    np_acts-logits-general · gemini-2.0-flash

    reverse and opposite

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     abstrait
    -0.46
    atisfactory
    -0.45
     immédi
    -0.44
     capitolo
    -0.44
    まと
    -0.43
     hạn
    -0.42
     ErrIntOverflow
    -0.42
    essional
    -0.41
    lijf
    -0.41
    anskje
    -0.41
    POSITIVE LOGITS
     reverse
    2.79
     reversed
    2.60
     Reverse
    2.45
    reverse
    2.39
     reverses
    2.35
    Reverse
    2.33
     reversing
    2.27
     reversal
    2.26
    reversed
    2.14
     revers
    2.11
    Activations Density 0.582%

    No Known Activations