© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 9508
    Prev
    Next
    INDEX
    Explanations

    financial figures and related numeric data

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

    Numbers or roman numerals

    np_acts-logits-general · gemini-2.0-flash

    numbers and sequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rungsseite
    -0.71
     lunedì
    -0.66
     unknownFields
    -0.63
    Filmografie
    -0.62
    новниш
    -0.62
     Reine
    -0.62
    PRNewswire
    -0.62
    zysta
    -0.59
     Agamemnon
    -0.59
     
    -0.58
    POSITIVE LOGITS
            
    0.94
    3
    0.60
     XIII
    0.55
    十三
    0.53
     iii
    0.52
    thir
    0.52
    AndEndTag
    0.51
     Fonda
    0.50
    Wednesday
    0.50
    Wed
    0.49
    Activations Density 0.045%

    No Known Activations