© 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. 0-GEMMASCOPE-RES-16K
    11. 532
    Prev
    Next
    INDEX
    Explanations

    modal verbs and terms of insistence or refusal

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bootstrapcdn
    -0.82
    Portale
    -0.75
     propOrder
    -0.73
     myſelf
    -0.63
    RenderAtEndOf
    -0.63
    AddTagHelper
    -0.61
     ſind
    -0.60
     ſch
    -0.60
     ſever
    -0.60
    SourceChecksum
    -0.59
    POSITIVE LOGITS
     yes
    0.68
     yeah
    0.62
    yes
    0.60
     insisted
    0.58
     Fin
    0.54
     fancy
    0.54
     kept
    0.53
     hey
    0.52
     flush
    0.51
     insists
    0.50
    Activations Density 0.268%

    No Known Activations