Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 15215
    Prev
    Next
    INDEX
    Explanations

    references to group identities and the collective actions or sentiments within those groups

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

    Plural nouns of nationalities/locations

    np_acts-logits-general · gemini-2.0-flash

    people from a place or group

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     pinulongan
    -0.37
    #+#
    -0.35
    rawtypes
    -0.33
     seed
    -0.30
    GeoNames
    -0.30
    ("")]
    
    -0.29
     handing
    -0.29
     initial
    -0.29
     predator
    -0.29
     bull
    -0.28
    POSITIVE LOGITS
     ſind
    0.65
     Residents
    0.64
     queſta
    0.63
    therners
    0.63
    Residents
    0.60
     parishioners
    0.58
     countrymen
    0.57
     colonists
    0.57
     Yorkers
    0.56
     Warga
    0.56
    Activations Density 0.359%

    No Known Activations