© 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-2-2B
    4. Residual Stream - 16k
    5. 4-GEMMASCOPE-RES-16K
    6. 906
    Prev
    Next
    INDEX
    Explanations

    references to geographic regions, specifically in North America

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Geplaatst
    -0.92
    enumi
    -0.86
     Pacer
    -0.82
    sstream
    -0.81
     تانيه
    -0.79
    getItemId
    -0.77
     literario
    -0.77
     Krakowie
    -0.75
     Lul
    -0.75
     appellee
    -0.74
    POSITIVE LOGITS
     North
    2.13
    North
    1.94
     NORTH
    1.78
    north
    1.77
    NORTH
    1.76
     north
    1.65
     norte
    1.17
    北
    1.16
     Noord
    1.10
     Noth
    1.10
    Activations Density 0.064%

    No Known Activations