Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 8154
    Prev
    Next
    INDEX
    Explanations

    references to specific local services and products in Milton, including dating services

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .*")]
    -0.56
     ""],
    -0.46
    +:+
    -0.38
     pulumi
    -0.36
    หลาย
    -0.35
    AutoScaleMode
    -0.35
    protoimpl
    -0.33
    +#+#
    -0.32
    ğraf
    -0.32
    __["
    -0.32
    POSITIVE LOGITS
     ſind
    0.60
     queſta
    0.57
     actionMode
    0.57
     Houſe
    0.56
     bookId
    0.56
    ⟬
    0.56
     Majefty
    0.55
     noDo
    0.54
     ſche
    0.52
     zuſammen
    0.52
    Activations Density 0.115%

    No Known Activations