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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    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. 12451
    Prev
    Next
    INDEX
    Explanations

    conversations about personal experiences and preferences

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

    informal slang and profanity

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

    informal, chatty/social-media style tokens — slang, fillers, emotive interjections, colloquial first‑person phrases and emoticons.

    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
    delwed
    -0.63
    rungsseite
    -0.61
     EconPapers
    -0.58
     Italijanski
    -0.58
     الرياضيه
    -0.53
    KURZBESCHREIBUNG
    -0.53
    DockStyle
    -0.52
    észetes
    -0.52
    ękuję
    -0.52
     صوتيه
    -0.52
    POSITIVE LOGITS
    fuck
    0.55
     tryna
    0.47
     FUCK
    0.46
     shitty
    0.46
     wanna
    0.45
     fuckin
    0.44
     rappers
    0.44
     lmao
    0.44
     sucks
    0.44
     hella
    0.44
    Activations Density 0.288%

    No Known Activations