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. 12-GEMMASCOPE-RES-16K
    6. 14886
    Prev
    Next
    INDEX
    Explanations

    the beginning of new sections or paragraphs in the text

    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
     geweest
    -0.65
     MaterialApp
    -0.63
    beforeEach
    -0.61
     étranger
    -0.61
    ագրություններ
    -0.60
    SuspendLayout
    -0.60
    horabuena
    -0.59
    addContainerGap
    -0.59
    tvguidetime
    -0.58
    最快更新
    -0.58
    POSITIVE LOGITS
    REASONS
    2.68
     REASONS
    1.74
    Reasons
    1.47
     reasons
    1.41
     Reasons
    1.39
    reasons
    1.35
    Reason
    1.22
     reason
    1.18
     Reason
    1.14
    reason
    1.05
    Activations Density 0.015%

    No Known Activations