© 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. 6076
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to measurement and description of structures and characteristics, particularly in a scientific context involving tails

    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
     Hod
    -0.33
     Kub
    -0.32
     лин
    -0.30
    Attr
    -0.30
    zuk
    -0.29
     Fel
    -0.28
    تش
    -0.28
    }}^{
    -0.28
    uo
    -0.28
     Fre
    -0.28
    POSITIVE LOGITS
     tail
    3.09
     Tail
    2.69
     tails
    2.67
    Tail
    2.55
    tail
    2.55
     TAIL
    2.33
     Tails
    2.19
    tails
    2.16
    TAIL
    2.13
    Tails
    2.05
    Activations Density 0.539%

    No Known Activations