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. 261
    Prev
    Next
    INDEX
    Explanations

    terms related to broadcasting and its associated concepts

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

    "Broad" followed by a variety of words

    np_acts-logits-general · gemini-2.0-flash

    broad followed by these specific suffixes

    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
     صوتيه
    -1.12
    tagHelperRunner
    -1.03
    +#+#
    -0.85
     GenerationType
    -0.83
    出版年
    -0.81
    ngdoc
    -0.78
     оригіналу
    -0.77
    JspWriter
    -0.77
    WebElementEntity
    -0.75
     resourceCulture
    -0.74
    POSITIVE LOGITS
     Bro
    0.60
    casted
    0.60
     Broad
    0.59
    Broad
    0.58
     based
    0.57
    based
    0.57
     spectrum
    0.56
    Based
    0.56
     Based
    0.55
    spectrum
    0.53
    Activations Density 0.090%

    No Known Activations