© 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. 13015
    Prev
    Next
    INDEX
    Explanations

    words and phrases indicating uncertainty or probability

    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
     BoxFit
    -0.63
    UserScript
    -0.57
     henvisninger
    -0.53
     anisotropy
    -0.52
    TypedDataSet
    -0.51
     Initialized
    -0.50
    eriks
    -0.49
     AssemblyCompany
    -0.48
     entrants
    -0.48
     hjelp
    -0.48
    POSITIVE LOGITS
     probably
    0.79
    probably
    0.75
    Probably
    0.71
     Probably
    0.70
     برانيه
    0.57
     ungefähr
    0.55
     prolly
    0.54
     waarschijnlijk
    0.52
     wahrscheinlich
    0.51
    avía
    0.51
    Activations Density 0.173%

    No Known Activations