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. 10-GEMMASCOPE-RES-16K
    6. 13158
    Prev
    Next
    INDEX
    Explanations

    words related to substances and relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Vidite
    -0.82
     تضيفلها
    -0.79
    دانشنامهٔ
    -0.79
     venons
    -0.74
     pitié
    -0.73
     Pingback
    -0.68
     citoy
    -0.67
    Искәрмәләр
    -0.67
     Jérusalem
    -0.66
     sainte
    -0.66
    POSITIVE LOGITS
    glMatrixMode
    0.65
    ThroughAttribute
    0.64
    +#+
    0.63
    TemporalType
    0.62
    <em>
    0.57
    djangoproject
    0.57
    (!_
    0.56
    transQ
    0.55
    eigh
    0.55
     يتيمه
    0.54
    Activations Density 0.052%

    No Known Activations