© 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. 31-GEMMASCOPE-RES-16K
    11. 4178
    Prev
    Next
    INDEX
    Explanations

    negative or limiting expressions related to capability or possibility

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

    the contraction "can't" (cannot) and related negative capability statements expressing impossibility or inability.

    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
    OGND
    -0.52
    出版年
    -0.43
    espejo
    -0.41
     picante
    -0.40
     actionMode
    -0.39
    XmlAccessType
    -0.39
     formales
    -0.38
     verſ
    -0.38
     eſſ
    -0.37
     occaf
    -0.37
    POSITIVE LOGITS
     cannot
    0.61
     Cannot
    0.59
     truly
    0.55
     realistically
    0.54
    cannot
    0.54
     predict
    0.53
     expect
    0.52
    太
    0.51
     Truly
    0.50
     fathom
    0.50
    Activations Density 0.356%

    No Known Activations