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. 1-GEMMASCOPE-RES-16K
    6. 9365
    Prev
    Next
    INDEX
    Explanations

    non-zero values in numerical data or results

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    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
    -1.75
     itſelf
    -1.69
     ―――――
    -1.50
     Paglinawan
    -1.40
     Efq
    -1.36
     doubtnut
    -1.34
     iſt
    -1.34
    ſelves
    -1.34
     Monfieur
    -1.33
     Anſ
    -1.32
    POSITIVE LOGITS
    .
    1.40
    ,
    1.31
    ↵
    1.22
    <eos>
    1.21
     
    1.20
    ↵↵
    1.11
     of
    1.02
    !
    1.00
    ?
    1.00
    0.96
    Activations Density 0.472%

    No Known Activations