© 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. 14755
    Prev
    Next
    INDEX
    Explanations

    questions expressing skepticism or criticism

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

    Questions starting with "Why"

    np_acts-logits-general · gemini-2.0-flash

    why questions

    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
    /*
    -0.51
    flot
    -0.45
    ioutil
    -0.44
     Manche
    -0.43
     pli
    -0.42
     MAY
    -0.42
     gro
    -0.41
    lech
    -0.40
    ici
    -0.40
     MIGHT
    -0.40
    POSITIVE LOGITS
     EconPapers
    0.73
    InvalidProtocol
    0.72
    djangoproject
    0.72
     tartalomajánló
    0.71
     suddenly
    0.68
    principalTable
    0.67
     Photocase
    0.66
     Италијани
    0.66
    わざわざ
    0.64
    そんなに
    0.62
    Activations Density 0.093%

    No Known Activations