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. 16-GEMMASCOPE-RES-16K
    6. 12565
    Prev
    Next
    INDEX
    Explanations

    references to the term "original" in various contexts, indicating discussions about original versions or creations

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

    "original"

    np_acts-logits-general · gemini-2.0-flash

    original followed by specific nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Réponses
    -0.84
    #+#
    -0.77
     дописавши
    -0.76
    PMailer
    -0.71
    hnia
    -0.69
    IntegerField
    -0.69
    chaun
    -0.69
    astify
    -0.66
     AspNetCore
    -0.65
     voeten
    -0.65
    POSITIVE LOGITS
     ORIGINAL
    1.21
    Original
    1.20
     Original
    1.18
     original
    1.10
    ORIGINAL
    1.07
     orig
    1.01
    getOriginal
    1.00
     originals
    1.00
    original
    0.96
    原
    0.89
    Activations Density 0.063%

    No Known Activations