© 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-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 7739
    Prev
    Next
    INDEX
    Explanations

    technical jargon and statistical terms related to research methodologies

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

    "average" or values near "average"

    np_acts-logits-general · gemini-2.0-flash

    average and standard deviation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Chham
    -0.52
    astify
    -0.48
     AssemblyCulture
    -0.47
     informée
    -0.46
     onCreateView
    -0.46
     вікісторінку
    -0.46
     Gelände
    -0.43
    providedIn
    -0.41
    ритори
    -0.41
    Хьажоргаш
    -0.40
    POSITIVE LOGITS
     average
    2.02
    average
    1.73
     Average
    1.73
    Average
    1.73
    平均
    1.67
     AVERAGE
    1.55
     averages
    1.53
    AVERAGE
    1.53
     averaged
    1.52
     promedio
    1.48
    Activations Density 1.485%

    No Known Activations