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. 14-GEMMASCOPE-RES-16K
    6. 2891
    Prev
    Next
    INDEX
    Explanations

    statements or expressions that issue warnings or cautionary advice

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uxxxx
    -0.74
    lodash
    -0.59
     FetchType
    -0.57
     مرئيه
    -0.57
     للاسماء
    -0.56
    xb
    -0.55
    хьтан
    -0.55
     Holl
    -0.55
     rend
    -0.54
    sste
    -0.54
    POSITIVE LOGITS
     warning
    1.73
     warn
    1.72
     warnings
    1.64
     warns
    1.56
     warned
    1.55
     Warn
    1.51
     Warnings
    1.47
    warn
    1.47
     Warning
    1.45
     cautioned
    1.40
    Activations Density 0.073%

    No Known Activations