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. 20-GEMMASCOPE-RES-16K
    6. 1123
    Prev
    Next
    INDEX
    Explanations

    words related to identity and identification processes

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

    containing "fi" or "ff"

    np_acts-logits-general · gemini-2.0-flash

    words with fi, ifi, specif, dif

    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
    keo
    -0.55
    Immediate
    -0.53
    peh
    -0.52
     bande
    -0.51
    acq
    -0.50
    ếp
    -0.50
    الإنجليزية
    -0.49
    pF
    -0.49
     Minute
    -0.49
     hào
    -0.49
    POSITIVE LOGITS
     GenerationType
    0.74
     kasarigan
    0.70
    RenderAtEndOf
    0.67
     utafitiHapana
    0.67
    elemField
    0.65
    MemoryWarning
    0.64
    Identyfik
    0.61
     kaarangay
    0.60
    UnsafeEnabled
    0.57
     <>",
    0.57
    Activations Density 0.183%

    No Known Activations