© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 107541
    Prev
    Next
    INDEX
    Explanations

    instances of contrast or contradiction in statements

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

    actually

    np_acts-logits-general · gemini-2.5-flash-lite

    the copula (forms of the verb “to be”) when used to state, emphasize, or correct an assertion (predicative constructions expressing contrast or clarification).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    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
     GenerationType
    -0.64
     Autorizaciones
    -0.63
    Дереккөздер
    -0.60
    JspWriter
    -0.59
     &___
    -0.54
     nakalista
    -0.53
    __(/*!
    -0.52
     InputDecoration
    -0.50
     BoxDecoration
    -0.50
     ***!
    -0.50
    POSITIVE LOGITS
     stanga
    0.52
     sebenarnya
    0.46
     actually
    0.41
    Actually
    0.40
    rawdę
    0.40
     fapt
    0.39
     egentlig
    0.38
     Actually
    0.37
    gelijk
    0.37
     dreapta
    0.37
    Activations Density 0.243%

    No Known Activations