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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 7953
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and notation, particularly related to equations and expressions involving variables

    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
     Bento
    -0.63
    RTHOOK
    -0.60
     aio
    -0.59
    ChildScrollView
    -0.59
    ctest
    -0.58
     Republic
    -0.57
    IBOutlet
    -0.57
     Dike
    -0.56
     Artifact
    -0.56
     AIO
    -0.56
    POSITIVE LOGITS
     $\
    1.09
    $\
    0.89
    {$\
    0.69
     \
    0.67
     $(\
    0.63
     ($\
    0.63
     {$\
    0.62
    {\
    0.57
     "\
    0.55
    }{$\
    0.52
    Activations Density 0.350%

    No Known Activations