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. 11-GEMMASCOPE-RES-16K
    6. 5733
    Prev
    Next
    INDEX
    Explanations

    code-related structures, particularly involving lists and conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OfWork
    -0.70
    msgTypes
    -0.66
     purpoſe
    -0.66
     occaf
    -0.63
     bandou
    -0.62
     pleaſure
    -0.60
     houſe
    -0.58
     rağmen
    -0.58
    ſelf
    -0.56
     <=",
    -0.56
    POSITIVE LOGITS
    RegressionTest
    0.63
    WithIOException
    0.55
     early
    0.51
     ProtoMessage
    0.50
    ExecuteReader
    0.48
     –
    0.48
    次
    0.48
     period
    0.47
     --
    0.47
    ariate
    0.47
    Activations Density 0.386%

    No Known Activations