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. 21-GEMMASCOPE-RES-16K
    6. 2047
    Prev
    Next
    INDEX
    Explanations

    terms related to healthcare organizations and initiatives focused on community and local support

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 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
    tvguidetime
    -0.50
     tulee
    -0.36
    YOUTUBE
    -0.36
    naments
    -0.35
    tering
    -0.35
    eniendo
    -0.34
    climbing
    -0.34
    coring
    -0.34
     betreft
    -0.34
    tttt
    -0.34
    POSITIVE LOGITS
    TagMode
    0.75
     tartalomajánló
    0.67
    ViewImports
    0.66
    LookAnd
    0.64
    jspb
    0.63
    ंदीखरीदारी
    0.62
    nextProps
    0.59
    Portály
    0.59
    expandindo
    0.57
     Autorizaciones
    0.56
    Activations Density 0.612%

    No Known Activations