Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    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. 12433
    Prev
    Next
    INDEX
    Explanations

    elements related to legal actions or judicial terms

    oai_token-act-pair · gpt-4o-miniTriggered 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
    ActionCreators
    -0.53
    来说
    -0.52
    "]}
    -0.49
    而言
    -0.47
    {}",
    -0.46
    '],
    -0.46
    ']}
    -0.46
    來說
    -0.46
    来讲
    -0.45
    ']]
    -0.45
    POSITIVE LOGITS
    verwijspagina
    0.86
    Билгалдахарш
    0.86
     Audiodateien
    0.80
    bkz
    0.78
    rungsseite
    0.78
     تانيه
    0.77
    balleur
    0.76
     got
    0.74
     estekak
    0.69
     pinulongan
    0.66
    Activations Density 0.410%

    No Known Activations