© 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. 131
    Prev
    Next
    INDEX
    Explanations

    code syntax and structure related to string manipulation and indexing

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

    Code or mathematical expressions using brackets and symbols

    np_acts-logits-general · gemini-2.0-flash

    code indices or mathematical subscripts

    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
    rxjs
    -0.75
    findpost
    -0.73
    aarrggbb
    -0.72
    UrlEncoded
    -0.70
    DrawerToggle
    -0.67
    NameInMap
    -0.66
     विश्वसनीयता
    -0.64
    }?>
    -0.64
    Chham
    -0.63
    %)$
    -0.60
    POSITIVE LOGITS
    Geplaatst
    0.55
     mulai
    0.50
     Ansch
    0.49
    estart
    0.48
    ImageContext
    0.46
    AppMethodBeat
    0.45
    adí
    0.45
    pportun
    0.43
     emosi
    0.43
     Prefix
    0.43
    Activations Density 0.097%

    No Known Activations