© 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-2-9B
    7. Residual Stream - 16k
    9. 33-GEMMASCOPE-RES-16K
    11. 13335
    Prev
    Next
    INDEX
    Explanations

    references to books, movies, or other forms of media that deal with themes of unity and resistance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ValueStyle
    -0.47
     Audiodateien
    -0.36
     desempe
    -0.36
     voilà
    -0.36
    Composable
    -0.35
     overseeing
    -0.33
    junto
    -0.33
    preuve
    -0.32
    Datuak
    -0.31
    śnie
    -0.30
    POSITIVE LOGITS
     contain
    0.82
     contains
    0.77
     include
    0.73
     focuses
    0.73
     focus
    0.70
     includes
    0.70
     bevat
    0.67
     sisält
    0.67
     incorporates
    0.66
     incorporate
    0.66
    Activations Density 1.086%

    No Known Activations