© 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. 14185
    Prev
    Next
    INDEX
    Explanations

    elements related to emotional and psychological states or concepts

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

    after periods or at the start of sentences/context

    np_acts-logits-general · gemini-2.0-flash

    Cedar Grove, just one, better survival

    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
    x
    -0.56
    X
    -0.53
    in
    -0.52
    0
    -0.51
     x
    -0.51
     X
    -0.48
    อิน
    -0.45
    ×
    -0.45
     эк
    -0.44
    iner
    -0.44
    POSITIVE LOGITS
    #+#
    0.90
     مشين
    0.76
    Lähteet
    0.72
     betweenstory
    0.70
    sizeCache
    0.69
     defaultstate
    0.69
    NameInMap
    0.66
     Paglinawan
    0.66
    tagHelperRunner
    0.65
    RegressionTest
    0.64
    Activations Density 0.674%

    No Known Activations