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. 6637
    Prev
    Next
    INDEX
    Explanations

    situations involving technical installation processes and related issues

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

    "Once" or similar words

    np_acts-logits-general · gemini-2.0-flash

    once, after, completion

    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
    あえて
    -0.60
    DebuggerNonUser
    -0.50
    tionally
    -0.45
    ilians
    -0.45
    ってきました
    -0.44
    ული
    -0.44
     Jahren
    -0.42
     متعلقه
    -0.42
    chkin
    -0.42
    __(/*!
    -0.42
    POSITIVE LOGITS
     once
    2.99
     Once
    2.75
    Once
    2.74
    once
    2.63
     ONCE
    2.15
    ONCE
    2.13
    一旦
    1.89
     Sobald
    1.71
     sobald
    1.56
     after
    1.56
    Activations Density 0.497%

    No Known Activations