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. 19-GEMMASCOPE-RES-16K
    6. 2856
    Prev
    Next
    INDEX
    Explanations

    references to movement or relocation of people and families

    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
     дописавши
    -0.62
    GraphicsUnit
    -0.57
     BeautifulSoup
    -0.54
    HasAnnotation
    -0.53
     TextAppearance
    -0.49
    SuccessListener
    -0.48
    NameInMap
    -0.48
     autorytatywna
    -0.47
    SourceChecksum
    -0.46
     onError
    -0.46
    POSITIVE LOGITS
     move
    2.38
     relocation
    2.37
     moved
    2.29
     relocate
    2.27
     relocating
    2.23
     relocated
    2.20
     Move
    2.14
    move
    2.14
     moving
    2.11
     Moved
    2.05
    Activations Density 0.593%

    No Known Activations