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. 7119
    Prev
    Next
    INDEX
    Explanations

    numerical values and chemical components in scientific contexts

    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
     виправивши
    -0.71
    󠁴
    -0.64
    +#+#
    -0.62
     himo
    -0.61
     Italijani
    -0.59
    ➟
    -0.52
    bootstrapcdn
    -0.51
    󠁣
    -0.51
     estekak
    -0.49
    GHIJKLM
    -0.49
    POSITIVE LOGITS
    -------
    0.66
     confiable
    0.57
    uxxxx
    0.56
     étoit
    0.51
     duradero
    0.51
    citenamefont
    0.49
     Bewußt
    0.49
     quæ
    0.48
     enggak
    0.47
     adquis
    0.47
    Activations Density 4.147%

    No Known Activations