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-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 6894
    Prev
    Next
    INDEX
    Explanations

    phrases related to personal experiences and memory of learning skills

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     موا
    -0.33
     Achille
    -0.31
     cara
    -0.31
     analogy
    -0.30
     オート
    -0.30
     old
    -0.30
     Upper
    -0.29
     équ
    -0.29
    OrUpdate
    -0.29
     pozy
    -0.29
    POSITIVE LOGITS
    addPreferredGap
    0.72
     <<<<<<<<<<<<<<
    0.61
     väli
    0.59
    parsedMessage
    0.59
    addContainerGap
    0.59
     temporarily
    0.59
     hiatus
    0.59
    abestanden
    0.57
     Мексичка
    0.57
     يتيمه
    0.57
    Activations Density 0.580%

    No Known Activations