© 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. 5733
    Prev
    Next
    INDEX
    Explanations

    negative imperatives or cautions

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

    the phrase "Don't" at the beginning of sentences used as a negation or warning.

    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
     مواليد
    -0.50
    Rptr
    -0.49
    saraba
    -0.47
     мәгълү
    -0.47
    StoryboardSegue
    -0.47
     transfieras
    -0.46
     كمان
    -0.46
    PerformLayout
    -0.46
    Scénario
    -0.45
    TestBed
    -0.44
    POSITIVE LOGITS
     forget
    0.77
     underestimate
    0.67
     hesitate
    0.58
     worry
    0.57
     confuse
    0.54
     misunderstand
    0.53
     be
    0.51
     fooled
    0.51
     let
    0.51
    forget
    0.50
    Activations Density 0.073%

    No Known Activations