© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 13311
    Prev
    Next
    INDEX
    Explanations

    technical vocabulary related to genetics and molecular biology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ̈́
    -0.40
    CloseOperation
    -0.39
    ContentAlignment
    -0.38
     peccato
    -0.38
    larım
    -0.37
     gantung
    -0.37
     Vergnügen
    -0.36
    Tämä
    -0.35
    redients
    -0.35
     ErrIntOverflow
    -0.34
    POSITIVE LOGITS
     שוליים
    0.66
     vPvB
    0.64
    perative
    0.54
    Життєпис
    0.53
    athione
    0.49
    #+#
    0.49
    istocene
    0.48
     transference
    0.48
    onomia
    0.48
    Архівовано
    0.47
    Activations Density 2.223%

    No Known Activations