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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 2487
    Prev
    Next
    INDEX
    Explanations

    instances of the word "ap"

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

    starting with "ap" (case-insensitive)

    np_acts-logits-general · gemini-2.0-flash

    apse, apnoea, apartments, apolar

    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
    enumi
    -0.56
    IVEREF
    -0.55
     تضيفلها
    -0.51
    GenerationType
    -0.51
    RTRS
    -0.50
     autorytatywna
    -0.49
     correr
    -0.49
     già
    -0.48
    handleChange
    -0.48
    principalTable
    -0.48
    POSITIVE LOGITS
     Ap
    0.74
    Ap
    0.70
     AP
    0.67
     ap
    0.65
     APM
    0.61
     EAP
    0.61
     noqa
    0.59
     مرئيه
    0.59
     appo
    0.58
     Apu
    0.58
    Activations Density 0.070%

    No Known Activations