© 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. 11492
    Prev
    Next
    INDEX
    Explanations

    elements related to programming and user roles

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

    Code, models, and programming

    np_acts-logits-general · gemini-2.0-flash

    modelmodel and module related words

    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
     disambiguazione
    -0.69
     againſt
    -0.62
     Diſ
    -0.62
    IntoConstraints
    -0.60
    клопе
    -0.59
    BeginContext
    -0.58
    AndEndTag
    -0.57
    matchCondition
    -0.55
    seid
    -0.55
    astă
    -0.54
    POSITIVE LOGITS
     model
    1.38
    model
    1.25
     models
    1.23
     Model
    1.13
     Models
    1.11
    Model
    1.08
    models
    1.08
     MODEL
    1.08
    模型
    1.05
     modelo
    1.04
    Activations Density 0.224%

    No Known Activations