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. 13-GEMMASCOPE-RES-16K
    6. 8359
    Prev
    Next
    INDEX
    Explanations

    elements of fantasy and adventure in storytelling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_13/width_16k/average_l0_132
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Commencez
    -0.33
     ويكيميديا
    -0.32
    osť
    -0.32
    vosť
    -0.32
    BagConstraints
    -0.32
     bendera
    -0.32
     שב
    -0.32
     Ávila
    -0.31
    reathe
    -0.31
    EdgeInsets
    -0.30
    POSITIVE LOGITS
    Personendaten
    0.60
    Portail
    0.58
    Datuak
    0.52
     Efq
    0.50
    GEBURTSDATUM
    0.49
    ôtel
    0.48
    sizeCache
    0.46
    最快更新
    0.46
    
    0.45
    uitton
    0.44
    Activations Density 0.559%

    No Known Activations