© 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. 20-GEMMASCOPE-RES-131K
    11. 21656
    Prev
    Next
    INDEX
    Explanations

    mentions of URIs (Uniform Resource Identifiers)

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

    URI or URI followed by delimiter

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Fall
    -0.50
     abf
    -0.47
    Camb
    -0.47
    transQ
    -0.45
    AndEndTag
    -0.45
    LogManager
    -0.44
    Second
    -0.44
    Cold
    -0.43
     Fär
    -0.43
    ngdoc
    -0.43
    POSITIVE LOGITS
     URI
    1.09
    Uri
    1.07
     Uri
    1.05
     uri
    1.02
    uri
    0.98
    URI
    0.90
     Uribe
    0.85
    Uris
    0.65
     Uro
    0.60
     Urine
    0.60
    Activations Density 0.004%

    No Known Activations