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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    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. 9382
    Prev
    Next
    INDEX
    Explanations

    narrative elements associated with unusual and disturbing themes

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

    preceding adjectives describing something strange

    np_acts-logits-general · gemini-2.0-flash

    strange or unusual descriptions

    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
    bootstrapcdn
    -0.66
    ukses
    -0.60
    Vidite
    -0.55
    theoremstyle
    -0.55
    
    -0.54
    DockStyle
    -0.54
    Autoritní
    -0.54
    felizmente
    -0.52
     ilma
    -0.51
    iesis
    -0.50
    POSITIVE LOGITS
     strange
    2.52
     unusual
    2.43
     weird
    2.40
     odd
    2.37
     bizarre
    2.31
    strange
    2.14
    unusual
    2.13
     strangest
    2.11
     Unusual
    2.06
    weird
    2.04
    Activations Density 0.469%

    No Known Activations