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. 11783
    Prev
    Next
    INDEX
    Explanations

    input elements within a form in HTML

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

    HTML input types (radio, checkbox, submit, text)

    np_acts-logits-general · gemini-2.0-flash

    HTML input types

    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
     need
    -1.03
    Need
    -1.01
    need
    -1.00
     Need
    -0.96
     besoin
    -0.93
     needing
    -0.91
     Needs
    -0.87
     NEED
    -0.87
    Needs
    -0.87
    Needed
    -0.87
    POSITIVE LOGITS
    text
    0.68
     text
    0.60
    checkbox
    0.58
    submit
    0.55
    hidden
    0.53
    radio
    0.50
    ρας
    0.49
     Tana
    0.46
    number
    0.45
    Text
    0.44
    Activations Density 0.074%

    No Known Activations