© 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. 3-GEMMASCOPE-RES-16K
    11. 9828
    Prev
    Next
    INDEX
    Explanations

    descriptions of softness in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ArgumentParser
    -0.75
     Diz
    -0.71
    ActionCreators
    -0.66
    glEnd
    -0.64
    ("/:
    -0.63
    Clue
    -0.63
     beaker
    -0.63
    ganu
    -0.62
    FormTagHelper
    -0.62
    ủi
    -0.62
    POSITIVE LOGITS
     soft
    3.63
     Soft
    3.48
    soft
    3.36
    Soft
    3.33
     SOFT
    3.24
    SOFT
    2.90
     softness
    2.65
     softer
    2.58
     softly
    2.07
    软
    2.05
    Activations Density 0.044%

    No Known Activations