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. 7-GEMMASCOPE-RES-16K
    6. 5983
    Prev
    Next
    INDEX
    Explanations

    phrases that initiate lists or highlight specific details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     فريبيس
    -0.72
    ագրություններ
    -0.68
     صوتيه
    -0.67
    craper
    -0.65
    Parcelize
    -0.61
    iological
    -0.61
     AIM
    -0.61
     Raton
    -0.60
     Rainbow
    -0.59
     triple
    -0.59
    POSITIVE LOGITS
    Of
    1.29
     Of
    1.12
    OF
    1.02
     fallu
    0.99
     OF
    0.95
     disponibilités
    0.81
    OfWeek
    0.79
    JoinColumn
    0.77
    раздо
    0.77
     Bof
    0.76
    Activations Density 0.146%

    No Known Activations