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
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 6366
    Prev
    Next
    INDEX
    Explanations

    biological and programming terms related to cellular or molecular analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fevere
    -0.85
    ſelf
    -0.83
    ſelves
    -0.79
     Reſ
    -0.77
     Diſ
    -0.77
     ſte
    -0.77
     ſta
    -0.75
     Conſ
    -0.73
    AnchorStyles
    -0.72
     myſelf
    -0.71
    POSITIVE LOGITS
     trouverez
    0.38
     devriez
    0.30
    COP
    0.30
    ínű
    0.29
     стихи
    0.29
     blitt
    0.29
    fixtures
    0.29
    Events
    0.28
    žiai
    0.28
    js
    0.27
    Activations Density 0.894%

    No Known Activations