© 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-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 12966
    Prev
    Next
    INDEX
    Explanations

    negations and their context in sentences

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

    Tokens following "not"

    np_acts-logits-general · gemini-2.0-flash

    avoid or negation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MigrationBuilder
    -0.48
     Chwiliwch
    -0.45
    +#+#
    -0.45
    nehå
    -0.43
    MessageTagHelper
    -0.41
     تانيه
    -0.41
    __).
    -0.40
    ibrill
    -0.40
     الرياضيه
    -0.38
    LIS
    -0.38
    POSITIVE LOGITS
     avoiding
    0.57
    Avoiding
    0.56
     éviter
    0.54
     avoidable
    0.52
     Avoid
    0.52
     AVOID
    0.52
     Avoiding
    0.51
     '\\;'
    0.51
    avoid
    0.51
    避免
    0.51
    Activations Density 0.800%

    No Known Activations