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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 8446
    Prev
    Next
    INDEX
    Explanations

    references to spells and related terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DotNetBar
    -0.56
     defaultstate
    -0.56
    providedIn
    -0.54
    UnusedPrivate
    -0.52
     насељу
    -0.51
    Билгалдахарш
    -0.50
    codecSelfer
    -0.50
     xícara
    -0.46
     HttpNotFound
    -0.46
     للمعارف
    -0.46
    POSITIVE LOGITS
     spell
    0.78
     spelled
    0.65
    spell
    0.65
     spelling
    0.64
     Spell
    0.64
     Pel
    0.64
    pel
    0.62
    Pel
    0.60
     spells
    0.60
     pronounce
    0.59
    Activations Density 1.305%

    No Known Activations