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. 9117
    Prev
    Next
    INDEX
    Explanations

    technical terms related to programming and software components.

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

    code snippets from software development, particularly related to JavaScript and Angular modules.

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    references to importing or including code from other files or modules.

    oai_token-act-pair · claude-3-5-sonnet-20240620Triggered by @bot
    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
    r
    -0.43
    h
    -0.43
    +#+#
    -0.39
    o
    -0.37
    m
    -0.37
    集
    -0.36
    es
    -0.36
    u
    -0.36
    gląd
    -0.34
    *
    -0.34
    POSITIVE LOGITS
    Jeografia
    1.07
     للمعارف
    1.06
    GraphicsUnit
    1.04
    findpost
    0.99
    WriteBarrier
    0.97
     Мексичка
    0.93
    httphttps
    0.88
    Xna
    0.87
    хьтан
    0.87
     AttributeSet
    0.86
    Activations Density 0.028%

    No Known Activations