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. 18-GEMMASCOPE-RES-16K
    6. 10521
    Prev
    Next
    INDEX
    Explanations

    quotations and dialogue in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     виправивши
    -0.82
    verwijspagina
    -0.80
    rungsseite
    -0.79
    setViewportView
    -0.70
     tartalomajánló
    -0.69
     onAnimation
    -0.69
    ViewImports
    -0.64
    曖昧さ回避
    -0.63
    LookAnd
    -0.62
    <bos>
    -0.60
    POSITIVE LOGITS
     “
    1.10
     "
    1.00
     ”
    0.79
     “.
    0.76
     „
    0.76
     “…
    0.73
     “...
    0.71
    “
    0.71
    “.
    0.71
    “…
    0.69
    Activations Density 0.050%

    No Known Activations