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. 3-GEMMASCOPE-RES-16K
    6. 1575
    Prev
    Next
    INDEX
    Explanations

    Java package and import statements, specifically those related to AWS services and JSON processing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     myſelf
    -1.65
     Efq
    -1.47
     Monfieur
    -1.41
     itſelf
    -1.36
     tartalomajánló
    -1.32
     ſeveral
    -1.28
     Theſe
    -1.28
     purpoſe
    -1.27
    ſelves
    -1.27
     ſever
    -1.25
    POSITIVE LOGITS
     
    1.18
     -
    0.83
    <b>
    0.77
    .
    0.76
     /
    0.76
    <eos>
    0.75
    ,
    0.75
     a
    0.73
     and
    0.73
     "
    0.73
    Activations Density 0.075%

    No Known Activations