© 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. 5021
    Prev
    Next
    INDEX
    Explanations

    modal verbs indicating capability or possibility

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

    the phrase "it can be" followed by an adjective or verb describing a potential outcome or characteristic.

    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
    s
    -0.45
    y
    -0.43
     ability
    -0.40
    gov
    -0.39
     feit
    -0.38
     Chief
    -0.36
    d
    -0.36
     Ta
    -0.36
     footing
    -0.36
     ri
    -0.35
    POSITIVE LOGITS
     conceivably
    0.81
     canst
    0.77
     fácilmente
    0.72
    easily
    0.69
     easily
    0.69
     durchaus
    0.69
    potentially
    0.68
    Easily
    0.68
     صوتيه
    0.68
     potentially
    0.67
    Activations Density 0.276%

    No Known Activations