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. 21-GEMMASCOPE-RES-16K
    6. 8291
    Prev
    Next
    INDEX
    Explanations

    forms of the verb "live" and related concepts of existence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/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.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bootstrapcdn
    -0.91
    IndentedString
    -0.82
     ModelExpression
    -0.74
     חיצוניים
    -0.74
     Normdatei
    -0.72
    RenderAtEndOf
    -0.71
    ImageContext
    -0.71
    IUrlHelper
    -0.70
    XmlAccessorType
    -0.70
     nonatomic
    -0.70
    POSITIVE LOGITS
     lived
    0.55
     vidas
    0.55
     vic
    0.53
     חיים
    0.52
     lives
    0.49
     heureux
    0.47
     off
    0.47
     living
    0.47
     up
    0.47
     fru
    0.46
    Activations Density 0.055%

    No Known Activations