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. 24-GEMMASCOPE-RES-16K
    6. 4691
    Prev
    Next
    INDEX
    Explanations

    elements of parenting and childhood fears

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    relating to locations in a house

    np_acts-logits-general · gemini-2.0-flash

    locations or rooms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/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.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BeginContext
    -0.63
     graft
    -0.55
     villages
    -0.52
     '\\;'
    -0.49
     eingeb
    -0.49
     inoc
    -0.49
     hectáreas
    -0.48
     lái
    -0.48
    Архівовано
    -0.47
    Fns
    -0.46
    POSITIVE LOGITS
     upstairs
    1.18
     downstairs
    1.18
    Upstairs
    0.99
     furniture
    0.97
     curtains
    0.96
     ceiling
    0.95
     bedroom
    0.94
     bedrooms
    0.94
     cupboards
    0.86
     rooms
    0.86
    Activations Density 0.335%

    No Known Activations