© 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. 18-GEMMASCOPE-RES-16K
    11. 2906
    Prev
    Next
    INDEX
    Explanations

    requests for audience engagement and feedback

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

    Followed by URLs or social media requests

    np_acts-logits-general · gemini-2.0-flash

    asking for shares and comments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     intime
    -0.52
    riwal
    -0.47
    untung
    -0.44
    metis
    -0.44
    englanniksi
    -0.43
     것이다
    -0.42
     chegada
    -0.42
     Trabajo
    -0.41
     oficio
    -0.40
    approx
    -0.40
    POSITIVE LOGITS
    TagMode
    0.92
    reportWebVitals
    0.81
     Normdatei
    0.80
    MemoryWarning
    0.73
    Bronnen
    0.72
    Share
    0.72
    SHARE
    0.71
     Share
    0.71
    InjectAttribute
    0.71
     Paglinawan
    0.69
    Activations Density 0.067%

    No Known Activations