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. 19-GEMMASCOPE-RES-16K
    6. 2120
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to feasibility and reliability in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     EconPapers
    -0.85
    __*/
    -0.82
    +#+#
    -0.81
     Roskov
    -0.80
    oredCriteria
    -0.74
    webElementXpaths
    -0.73
     protoimpl
    -0.72
    StoryboardSegue
    -0.72
     '\\;'
    -0.72
    تقاوى
    -0.70
    POSITIVE LOGITS
     chez
    0.74
     in
    0.73
     for
    0.69
     everywhere
    0.67
     toepassing
    0.66
     elsewhere
    0.65
     đối
    0.65
     when
    0.64
     käyt
    0.62
     unless
    0.60
    Activations Density 0.874%

    No Known Activations