© 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. 0-GEMMASCOPE-RES-16K
    6. 8256
    Prev
    Next
    INDEX
    Explanations

    occurrences of quantifiers and references to groups or quantities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    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
     itſelf
    -1.53
     ſind
    -1.50
    ^(@)
    -1.46
     Monfieur
    -1.46
     iſt
    -1.45
     Anſ
    -1.43
    ſelves
    -1.42
     ―――――
    -1.42
     дописавши
    -1.41
    POSITIVE LOGITS
    <eos>
    0.98
    ,
    0.89
    .
    0.84
    ↵
    0.83
    -
    0.83
     and
    0.83
     in
    0.82
     of
    0.82
     for
    0.79
     (
    0.75
    Activations Density 0.830%

    No Known Activations