© 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. 10-GEMMASCOPE-RES-16K
    6. 5970
    Prev
    Next
    INDEX
    Explanations

    specific scientific terminologies and references related to immunology and genetics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    orianCalendar
    -0.73
    BufferException
    -0.66
    roek
    -0.65
    '],$
    -0.64
    &__
    -0.63
    кономі
    -0.63
    createComponent
    -0.62
    )?;
    -0.62
    lujah
    -0.62
    Aiheesta
    -0.60
    POSITIVE LOGITS
    -
    1.65
    expandindo
    0.94
    ‑
    0.85
    ‐
    0.80
    -...
    0.73
    _
    0.66
    ־
    0.66
    –
    0.65
     Waray
    0.64
    -|
    0.59
    Activations Density 1.274%

    No Known Activations