© 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. 7665
    Prev
    Next
    INDEX
    Explanations

    verbs and phrases associated with possibility and necessity

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

    modal verbs and auxiliary verbs that express possibility, ability, or future action (like "can," "could," "will," "must").

    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
     незавершена
    -0.51
    ientôt
    -0.41
     Савезне
    -0.40
     nových
    -0.37
     sínt
    -0.37
     méri
    -0.37
    $-$\\
    -0.37
     OTHERS
    -0.35
     realisation
    -0.35
     ANOTHER
    -0.35
    POSITIVE LOGITS
     redraw
    0.57
     churn
    0.54
     coales
    0.54
     proactively
    0.53
     immerse
    0.53
     ascribe
    0.53
     use
    0.52
     actively
    0.52
     empathi
    0.51
    ftagPool
    0.51
    Activations Density 2.793%

    No Known Activations