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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 12-GEMMASCOPE-RES-16K
    6. 5420
    Prev
    Next
    INDEX
    Explanations

    phrases relating to intersections or connections between different elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    quién
    -0.56
    setupUi
    -0.47
    quellen
    -0.46
     signora
    -0.46
    BoxLayout
    -0.45
    Fuß
    -0.44
     each
    -0.44
    enis
    -0.44
    enschutz
    -0.44
    glUniform
    -0.43
    POSITIVE LOGITS
     Roskov
    1.06
     antara
    0.84
     BETWEEN
    0.81
     between
    0.79
    Between
    0.76
     Between
    0.75
     mellem
    0.74
     zwischen
    0.73
    enumii
    0.73
     betwixt
    0.70
    Activations Density 0.598%

    No Known Activations