© 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-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 38966
    Prev
    Next
    INDEX
    Explanations

    concentrations of solutions expressed in milliliters per microliter

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

    concentration units (mg/mL, µg/mL)

    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
     المعيارى
    -0.68
     frågan
    -0.58
    TemporalType
    -0.57
    dersfield
    -0.56
    
    -0.52
    BagConstraints
    -0.52
    تقاوى
    -0.52
     StringTokenizer
    -0.51
     alugar
    -0.51
     ***!
    -0.51
    POSITIVE LOGITS
    mL
    1.88
     mL
    1.59
    cL
    0.75
    dL
    0.72
    iL
    0.65
    dB
    0.65
    MeV
    0.63
     MeV
    0.62
     mA
    0.62
    mA
    0.62
    Activations Density 0.028%

    No Known Activations