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. 30577
    Prev
    Next
    INDEX
    Explanations

    emphasis or intensifiers, particularly variations of the word "really" and related affirmations

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

    intensifier "really"

    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
    rungsseite
    -0.79
    enumi
    -0.57
     informée
    -0.55
    ंदीखरीदारी
    -0.46
    astéroïdes
    -0.45
     syndic
    -0.45
     abz
    -0.45
    tispiece
    -0.44
     setUsername
    -0.44
    ⎣
    -0.44
    POSITIVE LOGITS
    really
    1.17
     really
    1.15
    Really
    1.08
     REALLY
    1.06
     Really
    1.06
     realmente
    0.90
     gerçekten
    0.89
     realy
    0.87
     truly
    0.87
     vraiment
    0.85
    Activations Density 0.028%

    No Known Activations