© 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. 14811
    Prev
    Next
    INDEX
    Explanations

    concepts related to uncertainty and unexpected outcomes

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

    after negations (not, never, without)

    np_acts-logits-general · gemini-2.0-flash

    realize or acknowledge lack of knowledge

    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
    Hentet
    -0.62
     ISNI
    -0.59
    Personendaten
    -0.58
     GenerationType
    -0.56
    RegistryLite
    -0.54
    PullParser
    -0.51
    roch
    -0.51
    ьаж
    -0.50
    dyti
    -0.50
     automatiques
    -0.50
    POSITIVE LOGITS
     realize
    1.45
     realise
    1.37
     realizing
    1.33
     realizes
    1.30
     realising
    1.28
     realized
    1.27
     realises
    1.24
     realised
    1.23
     realization
    1.12
     realisation
    1.06
    Activations Density 0.195%

    No Known Activations