© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 230
    Prev
    Next
    INDEX
    Explanations

    occurrences of time-related indicators and sequences

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

    Time period after a preposition

    np_acts-logits-general · gemini-2.0-flash

    starts from time units

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Personensuche
    -0.67
     للمعارف
    -0.59
    +:+
    -0.56
     Roskov
    -0.56
     kteří
    -0.51
    afficheront
    -0.49
    říve
    -0.48
     ::=
    -0.47
    urezza
    -0.46
    TemporalType
    -0.45
    POSITIVE LOGITS
     Episode
    1.25
     Day
    1.23
     Chapter
    1.18
     Part
    1.16
    第
    1.14
    Episode
    1.06
     Phase
    1.05
     #
    1.04
     Stage
    1.04
     Week
    1.03
    Activations Density 1.854%

    No Known Activations