© 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. 21-GEMMASCOPE-RES-16K
    6. 13968
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to places

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

    geographic place names (proper nouns for towns, cities, counties, and regions).

    oai_token-act-pair · gpt-5Triggered by @arielgoldsteinlab

    say place-name endings

    np_max-act-logits · gpt-5Triggered by @arielgoldsteinlab
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ارتمان
    -0.56
     好文分享
    -0.56
     iprot
    -0.55
    ftagPool
    -0.52
    راسیون
    -0.52
    <unused41>
    -0.50
    <unused43>
    -0.50
    <unused20>
    -0.50
    tagHelperRunner
    -0.50
    <unused14>
    -0.50
    POSITIVE LOGITS
     South
    0.54
     City
    0.46
     West
    0.45
    South
    0.45
     North
    0.45
     città
    0.43
     town
    0.42
     city
    0.42
     Valley
    0.42
    City
    0.42
    Activations Density 0.332%

    No Known Activations