© 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. 13-GEMMASCOPE-RES-16K
    6. 8088
    Prev
    Next
    INDEX
    Explanations

    terms related to roofing materials and their characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_13/width_16k/average_l0_132
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    jsonwebtoken
    -0.50
    MessageOf
    -0.41
     puissant
    -0.39
    LOADED
    -0.38
    期刊论文
    -0.38
     yal
    -0.37
    NewUrlParser
    -0.36
    setTypeface
    -0.36
     заря
    -0.35
     Popov
    -0.34
    POSITIVE LOGITS
     homeowners
    0.65
     installers
    0.63
     homeowner
    0.58
     installer
    0.53
    Residential
    0.53
     installing
    0.52
     Installer
    0.50
     Install
    0.50
     Residential
    0.50
     installation
    0.49
    Activations Density 0.161%

    No Known Activations