© 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-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 3225
    Prev
    Next
    INDEX
    Explanations

    instances of organizational names and affiliations

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

    Within-word abbreviations or initials

    np_acts-logits-general · gemini-2.0-flash

    "LK", "CK", "RK" clusters

    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
    Not in Any Lists

    No Comments

    Negative Logits
     OFDb
    -0.64
     Mathieu
    -0.52
     Harrison
    -0.52
    setVerticalGroup
    -0.52
    SPATH
    -0.50
    æder
    -0.50
    HARR
    -0.48
    GeneratedValue
    -0.47
    extAlignment
    -0.47
    Mathieu
    -0.46
    POSITIVE LOGITS
     LK
    1.12
     CK
    1.11
     PK
    1.10
     MK
    1.08
     GK
    1.07
     RK
    1.07
    PK
    1.06
     NK
    1.06
    CK
    1.04
    pk
    1.04
    Activations Density 0.871%

    No Known Activations