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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 10915
    Prev
    Next
    INDEX
    Explanations

    terms related to model performance and limitations in statistical contexts

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

    preceding "is" or a form of "be"

    np_acts-logits-general · gemini-2.0-flash

    importance and validity of assumptions

    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
    aarrggbb
    -0.70
     linkovi
    -0.69
    AppMethodBeat
    -0.64
    lccn
    -0.63
    исленность
    -0.63
     disambiguazione
    -0.60
     autorytatywna
    -0.60
    usermodel
    -0.59
     synced
    -0.59
     GenerationType
    -0.58
    POSITIVE LOGITS
     generali
    0.66
     critica
    0.61
     operacional
    0.59
     banques
    0.58
     generales
    0.58
     problèmes
    0.57
     potentially
    0.53
     phénomènes
    0.53
     procedimentos
    0.53
     typically
    0.52
    Activations Density 2.093%

    No Known Activations