© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 13135
    Prev
    Next
    INDEX
    Explanations

    biological and biochemical processes related to signaling pathways and protein expressions

    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
     Grecs
    -0.38
     enfans
    -0.36
     stør
    -0.35
    iseite
    -0.34
    getProfile
    -0.32
     rembour
    -0.31
     voks
    -0.30
     samfun
    -0.30
     przeprowad
    -0.30
     artist
    -0.30
    POSITIVE LOGITS
    expandindo
    0.75
    MessageOf
    0.68
    $_['
    0.63
    AnimationsModule
    0.63
    __':
    0.62
    Aholisi
    0.61
     regulators
    0.60
    featureID
    0.60
    AddTagHelper
    0.60
     InputDecoration
    0.59
    Activations Density 1.720%

    No Known Activations