© 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-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 5937
    Prev
    Next
    INDEX
    Explanations

    phrases that use the verb "to be" in various contexts indicating states, conditions, or actions

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

    the passive voice construction "can be" followed by past participles or adjectives.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     able
    -0.56
     ability
    -0.45
    能够
    -0.43
    能
    -0.43
     Ability
    -0.43
     graag
    -0.42
     inevitably
    -0.42
     primarily
    -0.41
     not
    -0.40
     pouvoir
    -0.40
    POSITIVE LOGITS
    IntoConstraints
    0.77
     fácilmente
    0.74
    хьтан
    0.73
     conceivably
    0.72
     facilmente
    0.72
     anywhere
    0.70
     canst
    0.69
     easily
    0.69
     akár
    0.68
     Италијани
    0.68
    Activations Density 0.582%

    No Known Activations