© 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-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 11676
    Prev
    Next
    INDEX
    Explanations

    calls to action and invitations to participate in events or discussions

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

    preceding possessive pronouns

    np_acts-logits-general · gemini-2.0-flash

    positive adjectives or possessives

    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
     RSSSF
    -0.91
     photolibrary
    -0.85
    ówczas
    -0.81
     posteriori
    -0.78
     flesta
    -0.76
     ――――
    -0.76
     ་་
    -0.75
     itſelf
    -0.74
     myſelf
    -0.72
     Houſe
    -0.72
    POSITIVE LOGITS
     our
    1.09
     amazing
    0.90
     gorgeous
    0.90
     some
    0.89
     exciting
    0.89
     beautiful
    0.82
     your
    0.82
     incredible
    0.80
     stunning
    0.76
     awesome
    0.74
    Activations Density 0.328%

    No Known Activations