© 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. 24-GEMMASCOPE-RES-16K
    11. 7671
    Prev
    Next
    INDEX
    Explanations

    phrases related to positioning and movement in relation to physical objects

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

    Prepositions followed by possessive pronouns

    np_acts-logits-general · gemini-2.0-flash

    location relationships

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    meneu
    -0.58
    Izvori
    -0.49
    rubin
    -0.48
    ณา
    -0.48
    ässig
    -0.46
    cagon
    -0.46
    rogens
    -0.44
    Personendaten
    -0.43
    '}>
    -0.43
    OPSIS
    -0.43
    POSITIVE LOGITS
    ReusableCell
    0.86
     each
    0.84
     where
    0.82
    neath
    0.82
     either
    0.80
     itself
    0.79
    RegressionTest
    0.78
    VersionUID
    0.75
     underneath
    0.73
     eachother
    0.73
    Activations Density 0.395%

    No Known Activations