© 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-2-2B
    4. Residual Stream - 65k
    5. 13-GEMMASCOPE-RES-65K
    6. 38626
    Prev
    Next
    INDEX
    Explanations

    references to posts in a blogging or content management context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
     Мексичка
    -1.16
    __':
    
    -1.05
     متعلقه
    -1.05
    migrationBuilder
    -1.02
     cherchés
    -1.00
    continence
    -0.98
    
    -0.98
    LAUGHTER
    -0.98
    ]').
    -0.98
     Nieren
    -0.96
    POSITIVE LOGITS
     Post
    1.80
    Post
    1.79
    post
    1.73
     POST
    1.70
     post
    1.56
    POST
    1.55
     posts
    1.44
     Posts
    1.43
    Posts
    1.36
    posts
    1.30
    Activations Density 0.032%

    No Known Activations