© 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. 12752
    Prev
    Next
    INDEX
    Explanations

    references to numerical data and their implications

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

    Ordinal numbers after "its", "the", or "our"

    np_acts-logits-general · gemini-2.0-flash

    ordinal numbers after possessives

    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
    tagHelperRunner
    -0.58
    Diweddarwch
    -0.56
    AccessorTable
    -0.56
    Personendaten
    -0.56
    SerializedName
    -0.55
    PropertyChanging
    -0.55
    newswire
    -0.54
    yntaxException
    -0.50
    Билгалдахарш
    -0.49
     defaultstate
    -0.48
    POSITIVE LOGITS
     fifth
    3.01
     fourth
    2.92
     sixth
    2.91
     seventh
    2.89
     ninth
    2.80
     third
    2.77
     eighth
    2.74
     tenth
    2.57
    fifth
    2.50
    third
    2.44
    Activations Density 0.644%

    No Known Activations