© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 5-GEMMASCOPE-RES-16K
    11. 6009
    Prev
    Next
    INDEX
    Explanations

    references to "Cal" or "California" related terms, including names and institutions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    󠁮
    -0.67
     مؤرشف
    -0.65
    AndEndTag
    -0.63
     Distrito
    -0.63
     ciber
    -0.62
     оригіналу
    -0.60
     Loire
    -0.59
    ##
    -0.58
    Irlande
    -0.58
    Tikang
    -0.58
    POSITIVE LOGITS
     Cal
    2.45
    Cal
    2.37
     cal
    2.30
     CAL
    2.27
    cal
    2.18
    CAL
    2.11
     calibrate
    1.67
     Calvo
    1.48
     calibrated
    1.47
     calibr
    1.47
    Activations Density 0.089%

    No Known Activations