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. 6-GEMMASCOPE-RES-16K
    6. 12143
    Prev
    Next
    INDEX
    Explanations

    individuals with notable achievements or roles in various fields

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     StringTokenizer
    -0.44
     tinta
    -0.43
    șit
    -0.42
     —
    -0.38
     le
    -0.38
     šte
    -0.38
    ̀i
    -0.37
     site
    -0.36
    <eos>
    -0.36
    /
    -0.36
    POSITIVE LOGITS
     تضيفلها
    0.91
     Theſe
    0.87
     myſelf
    0.79
    ſelf
    0.77
     Jefus
    0.75
    qxd
    0.72
     Monfieur
    0.72
    KommentareTeilen
    0.72
     الحره
    0.71
     itſelf
    0.71
    Activations Density 0.444%

    No Known Activations