© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 3209
    Prev
    Next
    INDEX
    Explanations

    references to support, perseverance, and notable achievements amidst adversity

    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
     nahilalakip
    -0.65
    AddTagHelper
    -0.63
     ProtoMessage
    -0.62
    RuleContext
    -0.59
     autorytatywna
    -0.58
    adaptiveStyles
    -0.54
     Administrativna
    -0.52
    SequentialGroup
    -0.49
     resourceCulture
    -0.48
     Савезне
    -0.48
    POSITIVE LOGITS
     تضيفلها
    0.45
     hope
    0.42
    Hope
    0.41
    Bang
    0.41
     rând
    0.40
     samfun
    0.40
    Te
    0.39
     AssemblyProduct
    0.39
    Cheers
    0.39
     hoffen
    0.38
    Activations Density 0.239%

    No Known Activations