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. 18-GEMMASCOPE-RES-16K
    6. 829
    Prev
    Next
    INDEX
    Explanations

    references to numerical data or values in various contexts

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

    The number 6

    np_acts-logits-general · gemini-2.0-flash

    number 6

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yarnpkg
    -0.99
    andExpect
    -0.98
    بوابة
    -0.95
     Legg
    -0.95
    errHandler
    -0.94
    Portail
    -0.92
     ivelany
    -0.90
    ibatis
    -0.88
    ukone
    -0.87
     CreateTagHelper
    -0.83
    POSITIVE LOGITS
    6
    1.38
    ⁶
    0.90
    7
    0.86
    5
    0.82
    4
    0.80
    ers
    0.79
     Sixers
    0.77
    8
    0.76
     SIX
    0.71
    six
    0.69
    Activations Density 0.857%

    No Known Activations