© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 4486
    Prev
    Next
    INDEX
    Explanations

    references to urban areas and their characteristics

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

    urban areas and towns

    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
     autorytatywna
    -0.53
     propOrder
    -0.52
    +#+
    -0.47
     externi
    -0.47
    \{\\
    -0.46
    weightedMode
    -0.45
     linkovi
    -0.45
    dismo
    -0.44
    GraphicsUnit
    -0.44
     NSCoder
    -0.44
    POSITIVE LOGITS
     city
    0.42
     urban
    0.39
     town
    0.39
     Photocase
    0.39
     streets
    0.38
     City
    0.37
     Streets
    0.37
     StatefulWidget
    0.37
     gynnwys
    0.36
     mayor
    0.36
    Activations Density 0.103%

    No Known Activations