© 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-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 8457
    Prev
    Next
    INDEX
    Explanations

    terms related to inventions and innovations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    that start with "in"

    np_acts-logits-general · gemini-2.0-flash

    instrumental variables, instruction set, inverted repeats

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •Steering experiments: Gemma 2-2B / 10-GEMMASCOPE-RES-16K

    No Comments

    Negative Logits
    roli
    -0.56
     aureus
    -0.55
     itali
    -0.54
    modelBuilder
    -0.53
    modb
    -0.53
     inert
    -0.52
    winston
    -0.52
    windowFixed
    -0.52
    PhysRevLett
    -0.51
     anglès
    -0.50
    POSITIVE LOGITS
     متعلقه
    1.01
     itſelf
    0.86
    .*")]
    0.80
     myſelf
    0.77
    Portale
    0.76
    ."</
    0.69
    """.
    0.68
     Abonnez
    0.65
    ]))
    
    0.64
     himſelf
    0.62
    Activations Density 0.684%

    No Known Activations