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
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 136
    Prev
    Next
    INDEX
    Explanations

    phrases and concepts related to software development and its processes

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

    technical discussions about software development processes, releases, and engineering challenges.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Dean
    -0.40
    目前
    -0.40
     Jim
    -0.40
     lui
    -0.38
     recent
    -0.38
     עצ
    -0.38
    GEBURTS
    -0.38
     was
    -0.36
     recientemente
    -0.36
     
    -0.36
    POSITIVE LOGITS
    rungsseite
    0.59
    AsUp
    0.59
     ब्रेकडाउन
    0.55
    QMetaType
    0.54
     vectorielle
    0.53
    ViewFeatures
    0.52
    tvguidetime
    0.52
     queſta
    0.51
    tanleria
    0.50
    XmlAccessType
    0.49
    Activations Density 0.293%

    No Known Activations