Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 11-GEMMASCOPE-RES-16K
    6. 5505
    Prev
    Next
    INDEX
    Explanations

    instances of the beginning of sentences or phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     المعيارى
    -0.78
     linkovi
    -0.76
     فريبيس
    -0.71
     GenerationType
    -0.71
     beginnetje
    -0.69
    PyExc
    -0.66
     دیکھیے
    -0.65
    ganu
    -0.63
    PhysRevLett
    -0.63
    ilíbrio
    -0.63
    POSITIVE LOGITS
     nakalista
    0.59
    ">//
    0.56
    Autoritní
    0.54
     transposition
    0.52
    addContainerGap
    0.47
     faveur
    0.46
    <eos>
    0.45
     coward
    0.43
    љено
    0.43
    mø
    0.42
    Activations Density 0.199%

    No Known Activations