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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 1617
    Prev
    Next
    INDEX
    Explanations

    terms related to economic and governmental regulations or influences

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

    Code, paths, and parameters

    np_acts-logits-general · gemini-2.0-flash

    mining and resources

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     itſelf
    -0.86
    Vidite
    -0.86
     ***!
    -0.82
     AssemblyCulture
    -0.81
     تضيفلها
    -0.78
    makeConstraints
    -0.78
     '\\;'
    -0.77
     myſelf
    -0.76
     Efq
    -0.75
     houſe
    -0.75
    POSITIVE LOGITS
     benne
    0.48
     ser
    0.44
    ilina
    0.43
    MINE
    0.41
     therein
    0.41
    LIBR
    0.40
    薬品
    0.40
     roupa
    0.40
     Chemical
    0.39
    port
    0.39
    Activations Density 0.589%

    No Known Activations