© 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-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 65769
    Prev
    Next
    INDEX
    Explanations

    geographical locations and their associated boundaries

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

    state border locations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     africano
    -0.46
     global
    -0.45
     mondial
    -0.44
     globales
    -0.44
     globale
    -0.42
     AdapterView
    -0.42
    Europa
    -0.42
     Europa
    -0.41
    global
    -0.41
     weltweit
    -0.40
    POSITIVE LOGITS
     border
    1.50
     Border
    1.29
    border
    1.24
    Border
    1.17
     BORDER
    1.15
     bordering
    1.11
     borders
    1.10
     neighbouring
    1.08
     frontière
    1.03
     Borders
    1.00
    Activations Density 0.110%

    No Known Activations