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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 22-GEMMASCOPE-RES-16K
    6. 14931
    Prev
    Next
    INDEX
    Explanations

    references to systemic power dynamics and their implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OCCURRED
    -0.46
    deelte
    -0.42
    BufferException
    -0.42
     AssemblyTitle
    -0.42
     pero
    -0.41
     ngunit
    -0.41
    astéroïdes
    -0.40
    <?
    -0.39
    avadoc
    -0.38
    cupa
    -0.38
    POSITIVE LOGITS
    脚注の使い方
    0.52
    ագրություններ
    0.46
    tangentMode
    0.45
     aukš
    0.43
     Misalnya
    0.43
    tivitas
    0.43
    তথ্যসূত্র
    0.42
    enderror
    0.42
     juos
    0.42
    Kjelder
    0.41
    Activations Density 0.560%

    No Known Activations