© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 25-GEMMASCOPE-RES-16K
    6. 9876
    Prev
    Next
    INDEX
    Explanations

    various forms of nouns and their associated morphological elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Datuak
    -0.64
     À
    -0.60
    WithIdentifier
    -0.59
     <<<<<<<<<<<<<<
    -0.54
    ChildScrollView
    -0.53
     Ü
    -0.52
    enumii
    -0.51
     Een
    -0.50
     ZA
    -0.49
     american
    -0.49
    POSITIVE LOGITS
     avoient
    1.33
     feroit
    1.30
     démocr
    1.28
     étoient
    1.27
     quelcon
    1.22
     colorés
    1.20
     chré
    1.18
     auroit
    1.18
     varandra
    1.17
     automatiques
    1.13
    Activations Density 0.131%

    No Known Activations