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-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 12428
    Prev
    Next
    INDEX
    Explanations

    usage of the letter 'c' in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 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
    InjectAttribute
    -0.96
     '\\;'
    -0.95
    saraba
    -0.75
     himo
    -0.71
    Искәрмәләр
    -0.69
    Personensuche
    -0.67
     frukt
    -0.66
    nocache
    -0.65
    MigrationBuilder
    -0.65
     Monfieur
    -0.65
    POSITIVE LOGITS
     c
    0.87
     getC
    0.57
    躇
    0.51
    ollectionView
    0.47
    dafx
    0.46
     meningitis
    0.44
    ("")]
    0.43
    lamin
    0.43
    assic
    0.43
    poy
    0.43
    Activations Density 0.308%

    No Known Activations