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-2-2B
    4. Residual Stream - 16k
    5. 19-GEMMASCOPE-RES-16K
    6. 428
    Prev
    Next
    INDEX
    Explanations

    text related to political statements and actions regarding social issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nakalista
    -0.84
    ьаж
    -0.80
    AccessorTable
    -0.79
    LookAnd
    -0.77
    
    -0.70
     Dulles
    -0.70
     surla
    -0.69
    ReusableCell
    -0.68
     Pyrr
    -0.68
    المكان
    -0.67
    POSITIVE LOGITS
     neighborhood
    1.04
     Neighborhood
    0.87
     neighbourhood
    0.82
    Neighborhood
    0.80
     neighborhoods
    0.77
    neighborhood
    0.73
     vecind
    0.73
     NEIGH
    0.69
     barrio
    0.68
     Neighbourhood
    0.68
    Activations Density 0.193%

    No Known Activations