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. 5805
    Prev
    Next
    INDEX
    Explanations

    recording and transcribing activities related to interviews and documentation processes

    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
     Bioinformatics
    -0.49
    หวัด
    -0.48
    Ecotoxicity
    -0.47
    disambiguation
    -0.46
    ifrance
    -0.45
     Heartland
    -0.45
    hetamine
    -0.45
     chêne
    -0.45
    bahasa
    -0.45
    XmlType
    -0.45
    POSITIVE LOGITS
     capture
    0.97
     capturing
    0.96
     recording
    0.95
     recorder
    0.88
     Capture
    0.87
    Capture
    0.86
     captures
    0.86
     recorders
    0.84
     recordings
    0.84
    capture
    0.84
    Activations Density 0.458%

    No Known Activations