© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 8229
    Prev
    Next
    INDEX
    Explanations

    phrases indicating updates, reports, or mentions of issues and facts

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

    Preceding words of "here"

    np_acts-logits-general · gemini-2.0-flash

    here pointer

    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
     nonatomic
    -0.57
    nonatomic
    -0.57
     isComment
    -0.54
    Amicalement
    -0.54
    enumii
    -0.53
     وتسجيلات
    -0.51
    typeof
    -0.49
    NameInMap
    -0.49
    tonode
    -0.48
    ########.
    -0.47
    POSITIVE LOGITS
     here
    4.79
    here
    3.69
     aquí
    3.50
     Here
    3.33
    Here
    3.27
     ici
    3.20
     здесь
    3.13
     aqui
    3.12
     HERE
    3.04
     aici
    3.03
    Activations Density 1.769%

    No Known Activations