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. 4-GEMMASCOPE-RES-16K
    6. 3120
    Prev
    Next
    INDEX
    Explanations

    sections of code or programming constructs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GraphicsUnit
    -0.71
     ***!
    -0.68
    tvguidetime
    -0.65
    DOCTYPE
    -0.65
    SpringBootTest
    -0.62
    sidemargin
    -0.58
     Administrativna
    -0.58
     باخ
    -0.58
    SOUNDBITE
    -0.58
    setViewportView
    -0.57
    POSITIVE LOGITS
    󠁿
    0.82
    μβρίου
    0.67
    irited
    0.62
    wiek
    0.62
    ыгана
    0.60
    ห์
    0.59
    ய்ய
    0.59
    >())
    0.57
    entrion
    0.56
     ')[
    0.55
    Activations Density 0.273%

    No Known Activations