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. 2236
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "up" and its variations

    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
    出版年
    -0.80
     themſelves
    -0.78
     himſelf
    -0.77
     itſelf
    -0.77
     obſ
    -0.75
     pleaſure
    -0.74
     whoſe
    -0.71
     faſt
    -0.71
    VIAF
    -0.71
    mergeFrom
    -0.71
    POSITIVE LOGITS
     front
    0.55
    EndContext
    0.53
    close
    0.47
    com
    0.47
    dat
    0.46
    gra
    0.45
    set
    0.45
    front
    0.45
    town
    0.44
     ups
    0.44
    Activations Density 0.079%

    No Known Activations