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. 6760
    Prev
    Next
    INDEX
    Explanations

    terms related to statistical models and assumptions

    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
     no
    -0.27
    sqr
    -0.26
     chat
    -0.26
    Ể
    -0.25
     chart
    -0.24
     aleg
    -0.24
     Baum
    -0.24
     Chat
    -0.24
     and
    -0.24
     issues
    -0.24
    POSITIVE LOGITS
     CreateTagHelper
    0.85
     Incorrect
    0.84
    Incorrect
    0.82
     incorrect
    0.80
    incorrect
    0.79
     correct
    0.79
     correctly
    0.79
    correctly
    0.77
    WithIOException
    0.77
    InputTagHelper
    0.76
    Activations Density 1.274%

    No Known Activations