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-2-2B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 806
    Prev
    Next
    INDEX
    Explanations

    Java code snippets and structure related to file handling and operational functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 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
     TextAppearance
    -0.80
     assoluto
    -0.52
     endblock
    -0.52
     Gladstone
    -0.51
     gard
    -0.50
     lievito
    -0.49
     utafitiHapana
    -0.49
    libft
    -0.48
     Mancini
    -0.48
     Gard
    -0.47
    POSITIVE LOGITS
     Thrift
    0.91
    thrift
    0.91
    Thrift
    0.89
     thrift
    0.86
    writeField
    0.70
    StructEnd
    0.69
     Antropo
    0.65
    BitSet
    0.64
     bone
    0.61
     TType
    0.61
    Activations Density 0.093%

    No Known Activations