© 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. 7-GEMMASCOPE-RES-16K
    6. 15113
    Prev
    Next
    INDEX
    Explanations

    references to people or groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_7/width_16k/average_l0_92
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ecraft
    -0.49
     OFDb
    -0.48
    faker
    -0.46
     ſind
    -0.45
     Ignite
    -0.44
     hasNext
    -0.43
     ſee
    -0.43
    isEdit
    -0.43
    EnableWeb
    -0.43
    sprzedam
    -0.43
    POSITIVE LOGITS
     those
    2.25
    those
    2.00
    Those
    1.93
     Those
    1.91
     THOSE
    1.77
    那些
    1.47
     aquellos
    1.43
     ceux
    1.42
    queles
    1.40
     thofe
    1.37
    Activations Density 0.088%

    No Known Activations