© 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. 9420
    Prev
    Next
    INDEX
    Explanations

    phrases related to medical conditions and treatments

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

    "stop" or ceasing of activity

    np_acts-logits-general · gemini-2.0-flash

    stopping or halting

    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
    zzleHttp
    -0.53
    сылкі
    -0.49
    })));
    -0.47
    Vidite
    -0.47
     Connectez
    -0.46
    ísmo
    -0.44
    ➟
    -0.44
     ✭✭
    -0.44
     useRouter
    -0.43
    bzero
    -0.43
    POSITIVE LOGITS
     stop
    3.23
     stopped
    2.99
     stopping
    2.99
     stops
    2.97
     Stop
    2.90
    stop
    2.85
    Stop
    2.77
     Stopping
    2.76
     STOP
    2.75
     Stops
    2.67
    Activations Density 0.791%

    No Known Activations