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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 16146
    Prev
    Next
    INDEX
    Explanations

    references to cabinets and their components or functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Storage furniture

    np_acts-logits-general · gemini-2.0-flash

    storage cabinets and drawers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SequentialGroup
    -0.70
    ьаж
    -0.69
    RenderAtEndOf
    -0.63
     CreateTagHelper
    -0.59
    rungsseite
    -0.55
     صوتيه
    -0.53
    InjectAttribute
    -0.52
    Życiorys
    -0.51
    Chham
    -0.50
     protoimpl
    -0.50
    POSITIVE LOGITS
     cabinet
    1.77
     cabinets
    1.67
     Cabinet
    1.65
    Cabinet
    1.55
     cupboard
    1.54
    cabinet
    1.54
     Cabinets
    1.51
     closet
    1.47
     cupboards
    1.46
     closets
    1.34
    Activations Density 0.053%

    No Known Activations