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-2-9B-IT
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 16276
    Prev
    Next
    INDEX
    Explanations

    phrases related to the concept of "natural" in various contexts

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

    "natural" or "naturally"

    np_acts-logits-general · gemini-2.0-flash

    natural occurring extension

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    帖最后由
    -0.54
    writerow
    -0.51
    RegressionTest
    -0.45
     faſt
    -0.42
    Chham
    -0.41
     diſt
    -0.40
     fevere
    -0.40
     paſſ
    -0.39
     Eſ
    -0.39
    ="@+
    -0.39
    POSITIVE LOGITS
     naturally
    2.73
    naturally
    2.38
     natural
    2.25
     Naturally
    2.14
    Naturally
    2.11
     naturalmente
    2.09
     naturellement
    2.09
    natural
    2.06
    自然
    2.02
     naturale
    1.95
    Activations Density 0.685%

    No Known Activations