© 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. 9-GEMMASCOPE-RES-131K
    11. 58576
    Prev
    Next
    INDEX
    Explanations

    references to geographic coordinates, particularly latitude and longitude

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

    variation and latitude

    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
     Públicas
    -0.53
     Púb
    -0.48
     Roskov
    -0.47
    ientôt
    -0.47
     Trabal
    -0.43
    =$((
    -0.41
    AndFlush
    -0.40
     članak
    -0.40
    )((
    -0.40
    ((
    -0.40
    POSITIVE LOGITS
     latitude
    2.17
     Latitude
    1.95
    latitude
    1.86
    Latitude
    1.83
     latitudes
    1.47
     longitude
    1.21
    getLatitude
    1.08
     Longitude
    1.03
    Longitude
    0.98
    longitude
    0.94
    Activations Density 0.004%

    No Known Activations