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. 8-GEMMASCOPE-RES-16K
    6. 15181
    Prev
    Next
    INDEX
    Explanations

    evidence from scientific studies and research findings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/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.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fortawesome
    -0.80
    gatsby
    -0.79
    tagHelperRunner
    -0.77
    twimg
    -0.70
    Erreferentziak
    -0.65
    MENAFN
    -0.65
     صوتيه
    -0.63
    textTheme
    -0.62
    rusted
    -0.59
    例文帳に追加
    -0.59
    POSITIVE LOGITS
     proven
    0.88
     empirically
    0.75
     observed
    0.70
    proven
    0.68
     evidence
    0.68
     blijkt
    0.66
     terbukti
    0.64
     demonstrated
    0.61
     proved
    0.60
     identified
    0.59
    Activations Density 0.576%

    No Known Activations