© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 19-GEMMASCOPE-RES-16K
    11. 2442
    Prev
    Next
    INDEX
    Explanations

    references to safety railings and their components or structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     autorytatywna
    -0.63
    viewDidLoad
    -0.62
    évaluateur
    -0.60
    JsonKey
    -0.60
     незавершена
    -0.58
    actionMode
    -0.55
     صوتيه
    -0.54
     nahilalakip
    -0.54
    AddTagHelper
    -0.52
    __((
    -0.51
    POSITIVE LOGITS
     fence
    1.92
     fences
    1.70
     fencing
    1.60
     Fence
    1.57
    fence
    1.50
     fenced
    1.41
    Fence
    1.39
     Fencing
    1.33
     barrier
    1.30
     barriers
    1.25
    Activations Density 0.131%

    No Known Activations