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. 16261
    Prev
    Next
    INDEX
    Explanations

    economic terms related to health and medical expenses

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

    Preceding a location mentioned alongside "alone"

    np_acts-logits-general · gemini-2.0-flash
    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
     <=",
    -0.37
     feltro
    -0.32
    wijze
    -0.30
    EnumType
    -0.30
    かというと
    -0.30
    ┑
    -0.30
    każ
    -0.29
    anstalt
    -0.28
     ocurre
    -0.28
    时候
    -0.28
    POSITIVE LOGITS
     alone
    3.72
    alone
    2.95
     ALONE
    2.86
     Alone
    2.78
    Alone
    2.42
     allein
    2.38
     alleine
    2.33
     alene
    2.31
     seul
    1.91
     sozinho
    1.87
    Activations Density 0.477%

    No Known Activations