© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 15337
    Prev
    Next
    INDEX
    Explanations

    special characters and numerical values, particularly in an analytical context

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

    Code or equation snippets

    np_acts-logits-general · gemini-2.0-flash

    Gustavo Cañete, Dose reduction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oa̍t
    -0.59
    RenderAtEndOf
    -0.55
     وسلم
    -0.48
    ignment
    -0.48
    ensitive
    -0.48
    PhysRev
    -0.47
    )}(\
    -0.45
    ineno
    -0.45
     cơm
    -0.45
    ództ
    -0.45
    POSITIVE LOGITS
    principalColumn
    0.66
     ✭✭
    0.59
     ContentValues
    0.58
     GenerationType
    0.58
     متعلقه
    0.58
    HasForeignKey
    0.57
     désolés
    0.54
    posedge
    0.53
    ագրություն
    0.53
     BitmapFactory
    0.52
    Activations Density 1.249%

    No Known Activations