© 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. 9949
    Prev
    Next
    INDEX
    Explanations

    significant milestones and achievements

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

    Start of a new chapter/phase

    np_acts-logits-general · gemini-2.0-flash

    new chapter or phase ending

    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
     hObject
    -0.63
    featureID
    -0.57
     Sucre
    -0.52
    ftagPool
    -0.52
    apiClient
    -0.52
    arım
    -0.51
    LookAnd
    -0.51
    clone
    -0.49
    فعل
    -0.47
    originally
    -0.47
    POSITIVE LOGITS
     chapter
    1.52
     chapters
    1.25
    chapter
    1.25
     capitolo
    1.09
    chapters
    1.03
     capítulo
    1.03
    Chapter
    1.02
     Chapter
    1.01
     chapitre
    1.01
     Kapitel
    0.96
    Activations Density 0.106%

    No Known Activations