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. 18-GEMMASCOPE-RES-16K
    6. 3189
    Prev
    Next
    INDEX
    Explanations

    modal verbs indicating obligation or potential in statements

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

    followed by auxiliary verbs

    np_acts-logits-general · gemini-2.0-flash

    modal verbs followed by "be"

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    viewDidLoad
    -0.63
    setViewportView
    -0.60
    rrggbb
    -0.59
    ]--;
    -0.58
    RegressionTest
    -0.55
    haustible
    -0.55
    AntiForgeryToken
    -0.54
     keyPressed
    -0.53
     useAppContext
    -0.53
     sobie
    -0.53
    POSITIVE LOGITS
     consist
    0.84
     occur
    0.74
     consisted
    0.71
     be
    0.71
     happen
    0.70
     existed
    0.69
     entail
    0.69
     consists
    0.67
     encompass
    0.66
     occurred
    0.66
    Activations Density 0.890%

    No Known Activations