© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 33-GEMMASCOPE-RES-16K
    6. 8177
    Prev
    Next
    INDEX
    Explanations

    elements related to programming functions and configuration management in software

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fxml
    -0.33
    android
    -0.30
    ejb
    -0.27
    jquery
    -0.26
     iPhone
    -0.25
     Halb
    -0.25
     Voll
    -0.25
    jQuery
    -0.25
     stadio
    -0.25
     le
    -0.23
    POSITIVE LOGITS
     Kubernetes
    0.82
    ☸
    0.76
     cluster
    0.73
     estekak
    0.71
     للمعارف
    0.71
    rungsseite
    0.71
    Kubernetes
    0.69
     Administrativna
    0.68
     للاسماء
    0.68
     orchestr
    0.68
    Activations Density 0.716%

    No Known Activations