© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 6013
    Prev
    Next
    INDEX
    Explanations

    forward-looking statements related to business expectations and regulations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     estekak
    -0.82
    FormTagHelper
    -0.77
    errHandler
    -0.72
     EClass
    -0.71
    Diwedd
    -0.67
    mergeFrom
    -0.63
    bootstrapcdn
    -0.62
    ExtendWith
    -0.62
    +:+
    -0.61
     defaultstate
    -0.61
    POSITIVE LOGITS
    argument
    1.41
    PRNewswire
    1.03
    ArgumentParser
    0.99
     argument
    0.93
     argparse
    0.85
    Argument
    0.82
     Argument
    0.82
    arguments
    0.71
    Einzelnachweise
    0.68
    addAttribute
    0.65
    Activations Density 0.025%

    No Known Activations