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. 1-GEMMASCOPE-RES-16K
    6. 15038
    Prev
    Next
    INDEX
    Explanations

    characters and sequences from specific naming conventions, likely related to technical identifiers or labeling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ViewFeatures
    -0.71
    nestjs
    -0.54
     Wikimedijinoj
    -0.54
    rrggbb
    -0.52
    Đây
    -0.51
     समीक्षाओं
    -0.49
    MemoryWarning
    -0.49
     EconPapers
    -0.49
     "..\..\
    -0.49
    +#+#
    -0.48
    POSITIVE LOGITS
    OT
    0.79
    OTH
    0.75
    ot
    0.70
    OY
    0.70
    oy
    0.67
    oris
    0.66
    ორ
    0.65
    oi
    0.65
    OW
    0.64
    OCH
    0.63
    Activations Density 0.592%

    No Known Activations