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-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 10942
    Prev
    Next
    INDEX
    Explanations

    elements related to programming constructs and data structures

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

    Code snippets with assignments

    np_acts-logits-general · gemini-2.0-flash

    assignment operators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     None
    -0.62
    None
    -0.61
     none
    -0.56
     nothing
    -0.53
    >[]
    -0.51
    =>'
    -0.51
    cadilly
    -0.49
    リュ
    -0.49
    Nothing
    -0.47
     ninguna
    -0.46
    POSITIVE LOGITS
    ंदीखरीदारी
    0.84
    GEBURTSDATUM
    0.81
     :=
    0.76
    expandindo
    0.74
    +#+#
    0.69
    AutoScale
    0.69
     bezeichneter
    0.66
    :=
    0.64
    تقاوى
    0.63
    StoryboardSegue
    0.61
    Activations Density 0.182%

    No Known Activations