© 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. 22-GEMMASCOPE-RES-16K
    6. 14489
    Prev
    Next
    INDEX
    Explanations

    character descriptions and attributes in a narrative context

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

    formality and coldness

    np_acts-logits-general · gemini-2.0-flash

    austere, formal, or stern descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    apunov
    -0.74
    \{\\
    -0.68
    RenderAtEndOf
    -0.67
     spéciaux
    -0.65
     librement
    -0.65
     insuffisamment
    -0.65
     démocr
    -0.63
     faibles
    -0.61
     libremente
    -0.61
    tangentMode
    -0.58
    POSITIVE LOGITS
     cold
    1.31
     austere
    1.18
     stern
    1.14
    cold
    1.13
     coldness
    1.12
     rigid
    1.09
     strict
    1.08
     coldly
    1.06
     stiff
    1.02
     dry
    0.99
    Activations Density 0.373%

    No Known Activations