Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 23790
    Prev
    Next
    INDEX
    Explanations

    repeated references to measurements in a text

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

    specific measurements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kysy
    -0.65
     piú
    -0.60
     nahilalakip
    -0.56
     aikaa
    -0.56
     dreapta
    -0.53
     dieux
    -0.52
     Мексичка
    -0.51
     šķ
    -0.51
     elétrico
    -0.50
     prohibido
    -0.50
    POSITIVE LOGITS
     measurements
    1.85
     Measurements
    1.75
    measurements
    1.67
     measurement
    1.63
    Measurements
    1.61
     Measurement
    1.56
    measurement
    1.55
    Measurement
    1.45
     MEASUREMENTS
    1.38
     MEASUREMENT
    1.28
    Activations Density 0.011%

    No Known Activations