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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 7475
    Prev
    Next
    INDEX
    Explanations

    phrases related to the interpretation of data and findings

    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
     nakalista
    -0.78
    orianCalendar
    -0.66
     Sex
    -0.66
     факт
    -0.65
    pox
    -0.64
     Bailly
    -0.64
    MILLIS
    -0.63
     XLV
    -0.62
    OfYear
    -0.62
    chastic
    -0.61
    POSITIVE LOGITS
     interpretations
    1.50
     interpretation
    1.48
     interprets
    1.44
     interpre
    1.44
     interpreting
    1.40
     interpret
    1.40
     interpreters
    1.37
     INTERPRET
    1.37
     Interpret
    1.37
     Interpretation
    1.36
    Activations Density 0.104%

    No Known Activations