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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 8040
    Prev
    Next
    INDEX
    Explanations

    names and proper nouns, particularly those related to people and locations

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

    Two-letter combinations ending in k

    np_acts-logits-general · gemini-2.0-flash

    words with k

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     EdgeInsets
    -0.78
    lawayo
    -0.77
    volo
    -0.71
    RectangleBorder
    -0.69
     &___
    -0.68
    vur
    -0.65
    dehy
    -0.62
    WriteBarrier
    -0.62
    NOST
    -0.61
    esModule
    -0.61
    POSITIVE LOGITS
    kkkk
    1.01
    kkk
    0.98
    k
    0.88
    ⓧ
    0.88
    kk
    0.83
     tsk
    0.80
    xk
    0.79
     Ruk
    0.79
     PKK
    0.79
     Duk
    0.78
    Activations Density 1.269%

    No Known Activations