© 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. 35-GEMMASCOPE-RES-16K
    11. 5397
    Prev
    Next
    INDEX
    Explanations

    terms related to extra or additional elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     weitere
    -0.40
     weiterer
    -0.39
     Ambiental
    -0.38
     further
    -0.36
     nærm
    -0.35
     dikel
    -0.34
     adequad
    -0.33
     zien
    -0.33
     Arque
    -0.33
     wyboru
    -0.33
    POSITIVE LOGITS
     Extra
    0.84
     EXTRA
    0.81
    ctable
    0.77
    polate
    0.76
    ordinary
    0.75
    ordin
    0.74
     curricular
    0.72
    marital
    0.70
    Extra
    0.68
    curricular
    0.67
    Activations Density 0.181%

    No Known Activations