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. 15-GEMMASCOPE-RES-16K
    6. 1447
    Prev
    Next
    INDEX
    Explanations

    statistical data related to population demographics and their socioeconomic status

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MLLoader
    -0.84
     CreateTagHelper
    -0.83
     ComVisible
    -0.82
     onCreateView
    -0.77
     onPostExecute
    -0.75
    ArgsConstructor
    -0.75
     للاسماء
    -0.75
     jScrollPane
    -0.74
     createState
    -0.73
     predominate
    -0.73
    POSITIVE LOGITS
     total
    0.59
     overall
    0.43
     dan
    0.42
     actually
    0.42
     totale
    0.42
     että
    0.41
     either
    0.40
     porte
    0.40
    irsch
    0.40
    kel
    0.40
    Activations Density 0.942%

    No Known Activations