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
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 11188
    Prev
    Next
    INDEX
    Explanations

    verbs and adjectives that convey strong emotional or impactful experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    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
    parsedMessage
    -0.74
     autorytatywna
    -0.62
     يتيمه
    -0.58
    Personendaten
    -0.57
    sidemargin
    -0.56
     المعيارى
    -0.55
     bezpiecze
    -0.54
    кобрита
    -0.54
    bukkit
    -0.54
    SOUNDBITE
    -0.54
    POSITIVE LOGITS
     exhilarating
    0.61
     upsetting
    0.57
     frustrating
    0.54
     enlightening
    0.54
    令人
    0.54
     alluring
    0.53
     exciting
    0.53
     damaging
    0.53
     destructive
    0.52
    Exciting
    0.51
    Activations Density 0.697%

    No Known Activations