© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 4975
    Prev
    Next
    INDEX
    Explanations

    terms related to data structures and programming attributes

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    Personendaten
    -0.51
     ब्रेकडाउन
    -0.45
     utafitiHapana
    -0.42
    ksessa
    -0.41
     faltan
    -0.38
    __);
    -0.37
     صوتيه
    -0.37
    wakilan
    -0.36
    ględ
    -0.36
     داشتند
    -0.36
    POSITIVE LOGITS
     become
    3.19
     becomes
    3.13
     becoming
    2.86
    become
    2.84
     Become
    2.75
     became
    2.72
    becomes
    2.72
     Becomes
    2.63
    Become
    2.61
    becoming
    2.53
    Activations Density 1.201%

    No Known Activations