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. 4-GEMMASCOPE-RES-16K
    6. 3543
    Prev
    Next
    INDEX
    Explanations

    geographic and administrative names associated with counties and regions

    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
    hassee
    -0.59
     chi̍t
    -0.49
     yours
    -0.47
     bagno
    -0.46
     redaktion
    -0.45
    pography
    -0.45
    mine
    -0.44
    名詞
    -0.44
    letka
    -0.44
    guli
    -0.44
    POSITIVE LOGITS
    hoga
    0.79
     cref
    0.71
     Broward
    0.69
    kesha
    0.68
    ptonshire
    0.68
     Metropolitan
    0.67
    Metropolitan
    0.66
     Gauteng
    0.65
     Middlesex
    0.62
    onshire
    0.62
    Activations Density 1.365%

    No Known Activations