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. 4618
    Prev
    Next
    INDEX
    Explanations

    elements related to image tags and their attributes in HTML/XML format

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

    HTML image source (`src`) attribute

    np_acts-logits-general · gemini-2.0-flash

    img src attributes

    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
     beginnetje
    -0.63
    Personendaten
    -0.62
    moveToFirst
    -0.62
    OGND
    -0.62
     typelib
    -0.62
    بوابة
    -0.59
     endblock
    -0.58
    Vidite
    -0.57
    UnusedPrivate
    -0.57
    AutoField
    -0.57
    POSITIVE LOGITS
     src
    1.41
    src
    1.32
    Src
    1.12
     Src
    1.04
     alt
    1.00
     SRC
    0.94
    SRC
    0.93
    alt
    0.85
    Alt
    0.80
     url
    0.79
    Activations Density 0.257%

    No Known Activations