Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 6899
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and their components related to functional analysis or statistics

    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
     surla
    -0.66
    +#+#
    -0.64
    styleType
    -0.62
     nakalista
    -0.61
    AndEndTag
    -0.60
    ExtendWith
    -0.59
     mijne
    -0.57
    IsMutable
    -0.57
     Numerade
    -0.57
     actionMode
    -0.56
    POSITIVE LOGITS
    :^(
    0.34
     East
    0.31
     disambiguazione
    0.30
     even
    0.29
     function
    0.28
     fog
    0.27
     potência
    0.27
     блу
    0.26
     baig
    0.26
     دیکھیے
    0.26
    Activations Density 1.537%

    No Known Activations