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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 25-GEMMASCOPE-RES-16K
    6. 3456
    Prev
    Next
    INDEX
    Explanations

    names of individuals and references to nationality or place of origin

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Tennessee
    -0.67
    Tennessee
    -0.65
     Allahabad
    -0.65
     Michigan
    -0.64
     Nashville
    -0.62
    Nashville
    -0.62
    Michigan
    -0.60
     idéia
    -0.59
     Knoxville
    -0.59
    NESSEE
    -0.58
    POSITIVE LOGITS
     Portugal
    1.44
     Portuguese
    1.36
     Lisbon
    1.33
    Portugal
    1.28
     Algarve
    1.17
     portug
    1.11
    Portuguese
    1.10
     portugal
    1.09
     Portug
    1.03
     Lisboa
    1.03
    Activations Density 0.164%

    No Known Activations