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. 21-GEMMASCOPE-RES-16K
    6. 7372
    Prev
    Next
    INDEX
    Explanations

    SQL query statements that involve selecting data from tables

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    throw
    -0.44
    und
    -0.43
    would
    -0.42
    thus
    -0.40
    خص
    -0.40
    ResumeLayout
    -0.40
    <eos>
    -0.40
    φι
    -0.40
    bring
    -0.39
     Amaz
    -0.39
    POSITIVE LOGITS
    parsedMessage
    0.78
     فريبيس
    0.78
     WHERE
    0.74
    abestanden
    0.74
     للمعارف
    0.71
    omock
    0.71
     المعيارى
    0.70
    makeConstraints
    0.69
     AS
    0.68
    +#+#
    0.68
    Activations Density 0.102%

    No Known Activations