© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 14953
    Prev
    Next
    INDEX
    Explanations

    references to a specific topic or theme being discussed

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

    "On the" followed by a noun

    np_acts-logits-general · gemini-2.0-flash

    on the [noun phrase]

    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
    ]--;
    -0.63
    "}")
    -0.58
    outState
    -0.58
    TestingModule
    -0.57
    providedIn
    -0.57
    addCriterion
    -0.56
    endpush
    -0.54
    forests
    -0.53
    UnknownFieldSet
    -0.53
    HasBeenSet
    -0.53
    POSITIVE LOGITS
     behalf
    0.94
     contrary
    0.80
     basis
    0.74
     outskirts
    0.73
    rungsseite
    0.70
     verge
    0.70
     occasion
    0.69
     brink
    0.65
     cusp
    0.64
     periphery
    0.64
    Activations Density 0.133%

    No Known Activations