© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 1705
    Prev
    Next
    INDEX
    Explanations

    information about decision-making and options

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

    Expressing preference or choice

    np_acts-logits-general · gemini-2.0-flash

    choosing between options

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    marle
    -0.61
    Amour
    -0.50
     "@/
    -0.46
    [++
    -0.44
    
    -0.44
    sensi
    -0.43
    readdir
    -0.43
    \{\\
    -0.43
    tania
    -0.43
     overexpression
    -0.43
    POSITIVE LOGITS
     preference
    1.16
     choosing
    1.15
     choose
    1.15
     whichever
    1.11
     Choosing
    1.10
     preferred
    1.10
    Choosing
    1.08
    choose
    1.06
     chose
    1.05
     chosen
    1.03
    Activations Density 0.607%

    No Known Activations