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. 9-GEMMASCOPE-RES-16K
    6. 11286
    Prev
    Next
    INDEX
    Explanations

    roles and positions in sports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ddots
    -0.38
     doğum
    -0.37
     aña
    -0.36
    kedés
    -0.36
     erreurs
    -0.36
     evolucion
    -0.36
     rocas
    -0.35
     desbloquear
    -0.35
     ağaç
    -0.34
     çı
    -0.34
    POSITIVE LOGITS
    ьаж
    0.50
     forward
    0.49
     MainAxisSize
    0.47
     winger
    0.47
    ItemBackground
    0.47
    protoimpl
    0.47
     שוליים
    0.46
     FormsModule
    0.46
    SequentialGroup
    0.46
    InitStruct
    0.46
    Activations Density 0.302%

    No Known Activations