© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 40-GEMMASCOPE-RES-16K
    11. 3954
    Prev
    Next
    INDEX
    Explanations

    modal verbs and phrases indicating ability or necessity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    دانشنامهٔ
    -0.53
    Hentet
    -0.47
     Вікі
    -0.46
     autorytatywna
    -0.45
    DebuggerNonUser
    -0.45
     MainAxisSize
    -0.42
     MessageBoxIcon
    -0.42
    GOTREF
    -0.41
    enumii
    -0.41
    ])[
    -0.41
    POSITIVE LOGITS
     able
    3.05
     ability
    2.30
    Able
    1.98
     capaz
    1.94
     Able
    1.93
     Ability
    1.78
     capables
    1.73
     capable
    1.72
    Ability
    1.70
    能够
    1.68
    Activations Density 0.850%

    No Known Activations