© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 5813
    Prev
    Next
    INDEX
    Explanations

    geographical locations and regional names

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

    Geographic regions or place names

    np_acts-logits-general · gemini-2.0-flash

    U.S. states and regions

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    httphttps
    -0.56
     application
    -0.41
     scul
    -0.38
    醐
    -0.38
     atomic
    -0.37
    Demografie
    -0.37
    Lookup
    -0.36
    NaOH
    -0.35
    исленность
    -0.35
     skola
    -0.35
    POSITIVE LOGITS
    Valley
    0.64
    ScopeManager
    0.61
     resourceCulture
    0.60
     Valley
    0.59
    valley
    0.59
     betweenstory
    0.59
    parsedMessage
    0.57
     Region
    0.56
    bootstrapcdn
    0.56
     region
    0.55
    Activations Density 0.332%

    No Known Activations