© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 9039
    Prev
    Next
    INDEX
    Explanations

    structured data and HTML/CSS syntax

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

    CSS style attributes: top, left, opacity, position

    np_acts-logits-general · gemini-2.0-flash

    css positioning and opacity

    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
     comigo
    -0.49
     conmigo
    -0.48
     sauter
    -0.47
    Tabbed
    -0.45
    mence
    -0.43
    bolso
    -0.43
     schließt
    -0.42
    bello
    -0.42
     ricar
    -0.40
    Beruf
    -0.40
    POSITIVE LOGITS
    IsMutable
    0.93
     дописавши
    0.84
     NSCoder
    0.83
     GenerationType
    0.78
     mergeFrom
    0.71
     Normdatei
    0.65
    SourceChecksum
    0.64
    Rourke
    0.64
     CURLOPT
    0.64
    transform
    0.64
    Activations Density 0.171%

    No Known Activations