© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 4590
    Prev
    Next
    INDEX
    Explanations

    statements regarding personal beliefs and feelings about purpose and identity

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

    continuation or remaining

    np_acts-logits-general · gemini-2.0-flash

    things continue

    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
    MigrationBuilder
    -0.82
    protoc
    -0.51
    OGND
    -0.50
    setAccessible
    -0.46
    WithMany
    -0.45
     Савезне
    -0.45
    transparent
    -0.44
     Schnell
    -0.43
     Geral
    -0.43
     debut
    -0.42
    POSITIVE LOGITS
     still
    1.74
     continue
    1.70
     continued
    1.59
     continuing
    1.58
     continues
    1.56
    still
    1.55
     weiterhin
    1.52
    continue
    1.51
    continuing
    1.43
     continuance
    1.42
    Activations Density 0.704%

    No Known Activations