© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 25-GEMMASCOPE-RES-16K
    6. 9015
    Prev
    Next
    INDEX
    Explanations

    technical terms related to electrical measurements in scientific contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    principalTable
    -0.55
     bin
    -0.54
    Viitteet
    -0.51
     Dakota
    -0.50
     Normdatei
    -0.49
     Ader
    -0.48
    bulin
    -0.48
    kuuta
    -0.47
    cotch
    -0.47
     gynhyrchwyd
    -0.47
    POSITIVE LOGITS
     glow
    0.63
     ionization
    0.61
     BoxFit
    0.60
     Townsend
    0.58
     discharge
    0.57
     Italijanski
    0.56
     sputtering
    0.56
    glow
    0.55
     torr
    0.53
     cathode
    0.53
    Activations Density 1.150%

    No Known Activations