© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 7012
    Prev
    Next
    INDEX
    Explanations

    phrases that express the absence or lack of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    しまう
    -0.64
    menjadi
    -0.63
    duate
    -0.61
    cipais
    -0.60
     sklearn
    -0.60
    meyi
    -0.58
    cknow
    -0.57
    HostException
    -0.56
    TagHelpers
    -0.55
    otis
    -0.55
    POSITIVE LOGITS
     nothing
    3.34
    nothing
    3.08
     Nothing
    2.95
    Nothing
    2.95
     NOTHING
    2.68
    NOTHING
    2.48
     nothin
    2.06
     nichts
    1.99
     nada
    1.96
     rien
    1.90
    Activations Density 0.037%

    No Known Activations