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. 4571
    Prev
    Next
    INDEX
    Explanations

    instances of numerical values and references related to legal information

    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
     Diſ
    -0.67
     corred
    -0.63
    تقاوى
    -0.62
     diſt
    -0.60
     tys
    -0.59
     Inſ
    -0.56
     himſelf
    -0.55
     obligé
    -0.55
     anzi
    -0.54
     Reſ
    -0.54
    POSITIVE LOGITS
    ⓧ
    0.81
     صوتيه
    0.79
    ThroughAttribute
    0.75
    AndEndTag
    0.72
    ArrowToggle
    0.72
    Xna
    0.70
    enderror
    0.69
    AccessFile
    0.69
    RTDA
    0.68
    WebControls
    0.66
    Activations Density 0.163%

    No Known Activations