© 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. 2-GEMMASCOPE-RES-16K
    11. 6735
    Prev
    Next
    INDEX
    Explanations

    expressions of something being ineffective or without value

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     SwiftUI
    -0.54
     AssemblyCulture
    -0.52
     @"/
    -0.40
     exig
    -0.39
     apl
    -0.39
     Infórmanos
    -0.37
     disturbed
    -0.36
     psycopg
    -0.36
    PMailer
    -0.36
    Gambas
    -0.36
    POSITIVE LOGITS
     useless
    2.47
    useless
    2.23
     pointless
    2.16
    Useless
    2.05
     worthless
    1.94
     meaningless
    1.92
     inútil
    1.91
     inutile
    1.80
     futile
    1.64
     irrelevant
    1.55
    Activations Density 0.281%

    No Known Activations