Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 17797
    Prev
    Next
    INDEX
    Explanations

    instances of the word "not" and variations of it to identify negation

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

    aren't

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    itself
    -0.58
     itself
    -0.58
     is
    -0.54
    is
    -0.53
    的一个
    -0.51
     enfans
    -0.49
    ing
    -0.49
     IS
    -0.47
    does
    -0.46
     has
    -0.45
    POSITIVE LOGITS
    RefNanny
    0.67
     themselves
    0.67
     eivät
    0.66
     were
    0.64
     those
    0.63
     Were
    0.63
     are
    0.61
    ſelves
    0.61
    Were
    0.60
    themselves
    0.60
    Activations Density 0.098%

    No Known Activations