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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 11010
    Prev
    Next
    INDEX
    Explanations

    terms related to "resorption" or similar processes in various contexts

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

    starting with "Res" or "res"

    np_acts-logits-general · gemini-2.0-flash

    reshaping, results, resolutions, resizer

    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
    ViewImports
    -0.74
     tartalomajánló
    -0.72
    MLLoader
    -0.70
    providedIn
    -0.70
    Demikian
    -0.64
     vouloir
    -0.63
     Paglinawan
    -0.63
    complexContent
    -0.63
    SourceChecksum
    -0.61
    Personendaten
    -0.61
    POSITIVE LOGITS
     res
    0.93
     Res
    0.85
    Res
    0.82
     rés
    0.72
    res
    0.66
     rec
    0.65
     RES
    0.65
     OnInit
    0.61
     re
    0.57
     resistive
    0.55
    Activations Density 0.196%

    No Known Activations