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. 14374
    Prev
    Next
    INDEX
    Explanations

    elements and attributes related to user interface layout in programming code

    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
     consultato
    -0.44
    RTEE
    -0.42
     strto
    -0.35
    SourceChecksum
    -0.32
    犀
    -0.31
    HasColumnName
    -0.31
    <eos>
    -0.31
     impractica
    -0.30
    $_['
    -0.29
    енча
    -0.29
    POSITIVE LOGITS
     يتيمه
    0.76
    rungsseite
    0.66
     صوتيه
    0.63
    exels
    0.61
     فريبيس
    0.61
    HasAnnotation
    0.54
    ValueStyle
    0.54
     Redewendung
    0.52
    yntaxException
    0.51
     zelve
    0.51
    Activations Density 0.913%

    No Known Activations