© 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. 16-GEMMASCOPE-RES-16K
    6. 5303
    Prev
    Next
    INDEX
    Explanations

    structured data or formatted numerical information within a document

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

    Tokens within square brackets and numbers

    np_acts-logits-general · gemini-2.0-flash

    archaic or foreign words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     essential
    -0.58
     important
    -0.56
     crucial
    -0.53
     core
    -0.49
     relevant
    -0.48
     needed
    -0.48
    ITURE
    -0.48
     necessary
    -0.47
     اللا
    -0.47
     Sy
    -0.45
    POSITIVE LOGITS
     bezeichneter
    0.69
    MigrationBuilder
    0.68
     "..\..\
    0.65
     Monfieur
    0.65
    Personensuche
    0.65
     laiton
    0.65
     nahilalakip
    0.64
     disambiguazione
    0.63
     Anſ
    0.63
    AndEndTag
    0.62
    Activations Density 0.268%

    No Known Activations