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. 6013
    Prev
    Next
    INDEX
    Explanations

    references to original hypotheses or claims in a scientific context

    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
     विश्वसनीयता
    -0.53
    انجليز
    -0.47
    addPreferredGap
    -0.47
    ourable
    -0.47
     meglio
    -0.46
     transition
    -0.45
     آخرین
    -0.43
     Transition
    -0.43
    enumi
    -0.41
    transition
    -0.41
    POSITIVE LOGITS
     originals
    0.85
    InvalidProtocol
    0.80
     Wikimedijinoj
    0.74
     originales
    0.73
     originais
    0.71
    principalTable
    0.71
     original
    0.69
    ruptedException
    0.69
     orig
    0.65
     AssemblyCulture
    0.65
    Activations Density 0.622%

    No Known Activations