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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 10-GEMMASCOPE-RES-16K
    6. 10795
    Prev
    Next
    INDEX
    Explanations

    phrases related to programming functions and APIs for audio recording

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AccessorTable
    -0.82
    tvguidetime
    -0.80
    expandindo
    -0.69
    ISupport
    -0.63
    Revenir
    -0.62
    InstrumentedTest
    -0.62
    GEBURTS
    -0.62
     AssemblyProduct
    -0.62
    endphp
    -0.60
    脚注の使い方
    -0.60
    POSITIVE LOGITS
    مصادر
    0.55
     autorité
    0.51
     Partagez
    0.51
    VIAF
    0.49
    %@
    0.47
     विश्वसनीयता
    0.46
    cos
    0.45
     Atten
    0.44
     CURLOPT
    0.44
    dro
    0.44
    Activations Density 0.438%

    No Known Activations