© 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
    4. Residual Stream - 16k
    5. 28-GEMMASCOPE-RES-16K
    6. 8193
    Prev
    Next
    INDEX
    Explanations

    biographical details and events related to individuals' lives

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

    a place or location

    np_acts-logits-general · gemini-2.0-flash

    places of origin and residence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    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
    -0.43
    RenderAtEndOf
    -0.41
    tagHelperRunner
    -0.40
    Mediabestanden
    -0.40
    //
    -0.38
    /***
    
    -0.35
    sizeCache
    -0.35
     manual
    -0.34
     automatique
    -0.33
    //});
    -0.33
    POSITIVE LOGITS
     headquarters
    0.66
     location
    0.65
     headquartered
    0.63
     reside
    0.61
     Location
    0.60
     LOCATION
    0.60
     Locations
    0.60
     venue
    0.60
     Headquarters
    0.59
     locations
    0.59
    Activations Density 0.568%

    No Known Activations