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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 19-GEMMASCOPE-RES-16K
    6. 2046
    Prev
    Next
    INDEX
    Explanations

    references to genetic conditions and their effects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ContentAsync
    -0.60
    DoubleQuotes
    -0.59
    WebControls
    -0.59
    findpost
    -0.56
    StoryboardSegue
    -0.54
    nocześnie
    -0.54
     perpetuity
    -0.54
    מעות
    -0.54
    TagHelper
    -0.53
     sumpay
    -0.52
    POSITIVE LOGITS
     lack
    1.10
     factors
    0.98
     factores
    0.94
    lack
    0.86
    Lack
    0.86
     Lack
    0.84
    factors
    0.81
     fatores
    0.81
     faktor
    0.80
     عوامل
    0.78
    Activations Density 0.740%

    No Known Activations