© 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. 22-GEMMASCOPE-RES-16K
    11. 7247
    Prev
    Next
    INDEX
    Explanations

    references to relationships and interactions between individuals, particularly in hierarchical or authoritative contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 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
    Not in Any Lists

    No Comments

    Negative Logits
     toepassing
    -0.40
    AddTagHelper
    -0.38
    calaureate
    -0.38
     komis
    -0.36
     presiding
    -0.36
    🔀
    -0.36
     isinstance
    -0.36
     teore
    -0.35
    losa
    -0.35
     INVEST
    -0.35
    POSITIVE LOGITS
     assistants
    0.75
     assistant
    0.67
     aides
    0.63
     Assistants
    0.62
    assistant
    0.62
     uLocal
    0.62
     setia
    0.56
    ConstraintMaker
    0.56
    assist
    0.55
     servants
    0.54
    Activations Density 0.611%

    No Known Activations