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. 16-GEMMASCOPE-RES-16K
    6. 6136
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions involving sums and limits

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Mathematical expressions inside LaTeX

    np_acts-logits-general · gemini-2.0-flash

    sums and variables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ----</
    -0.77
    XmlAccessorType
    -0.76
    enderror
    -0.74
    iestety
    -0.68
     OnInit
    -0.67
    twimg
    -0.66
     Audiodateien
    -0.66
     مشين
    -0.64
    '])->
    -0.63
     beginnetje
    -0.62
    POSITIVE LOGITS
    substack
    0.64
     forState
    0.54
    jardin
    0.50
     loue
    0.50
    épendance
    0.49
    sprü
    0.48
     Murch
    0.47
     oath
    0.46
     stylistic
    0.46
    linec
    0.46
    Activations Density 0.476%

    No Known Activations