© 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-2-9B
    7. Residual Stream - 16k
    9. 33-GEMMASCOPE-RES-16K
    11. 10687
    Prev
    Next
    INDEX
    Explanations

    reference to written documents or letters, particularly in the context of grammar and structure

    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
    httphttps
    -0.93
     ब्रेकडाउन
    -0.89
    iſchen
    -0.82
    ſicht
    -0.80
    
    -0.80
    principalColumn
    -0.80
    rungsseite
    -0.80
    niſſe
    -0.79
     snippetHide
    -0.79
     deſſen
    -0.79
    POSITIVE LOGITS
     des
    0.49
     der
    0.38
     an
    0.34
    ys
    0.33
     a
    0.29
    sp
    0.27
    The
    0.27
     zur
    0.26
    ot
    0.26
    ,
    0.26
    Activations Density 0.084%

    No Known Activations