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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 12151
    Prev
    Next
    INDEX
    Explanations

    geographical direction terms

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

    geographic directional terms like "Northwest," "Northeast," and "Southeast."

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    scrapy
    -0.52
    RTCK
    -0.42
    tagHelperRunner
    -0.42
     '\\;'
    -0.41
     BytesLike
    -0.40
     Southern
    -0.39
    Southern
    -0.37
    keits
    -0.37
     southern
    -0.37
    InputLabel
    -0.36
    POSITIVE LOGITS
    WebServlet
    0.71
     quadrant
    0.61
    corner
    0.60
     corner
    0.60
    KommentareTeilen
    0.54
     CORNER
    0.53
    AddTagHelper
    0.50
    Corner
    0.48
     esquina
    0.48
    באנגלית
    0.46
    Activations Density 0.113%

    No Known Activations