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. 12-GEMMASCOPE-RES-16K
    6. 12913
    Prev
    Next
    INDEX
    Explanations

    mentions of authorship or creation details in text documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     StringTokenizer
    -0.52
     EClass
    -0.51
    ఔ
    -0.48
     prieš
    -0.48
    PMailer
    -0.47
     maailman
    -0.47
     çe
    -0.46
    addPreferredGap
    -0.46
    NewReader
    -0.45
     बच
    -0.43
    POSITIVE LOGITS
    #+#
    1.37
    +#+
    1.28
    :+:
    1.00
    ########.
    0.99
    KommentareTeilen
    0.80
    enumii
    0.72
     EconPapers
    0.67
     الحره
    0.65
    AnchorStyles
    0.64
    +:+
    0.64
    Activations Density 0.023%

    No Known Activations