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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 5979
    Prev
    Next
    INDEX
    Explanations

    patterns or structures related to data organization, likely in a coding or formatting context

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

    The number "4" or "fourth"

    np_acts-logits-general · gemini-2.0-flash

    number four

    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
     terça
    -0.74
    Third
    -0.66
     Third
    -0.66
     Tuesday
    -0.66
     Secondly
    -0.64
     Thirdly
    -0.63
     виправивши
    -0.63
     Second
    -0.60
     TUESDAY
    -0.60
     Wednesday
    -0.58
    POSITIVE LOGITS
     fourth
    0.97
    4
    0.93
    ④
    0.89
    ❹
    0.87
    fourth
    0.86
     Fourth
    0.81
     quartet
    0.79
     keempat
    0.77
    Fourth
    0.76
     quadruple
    0.76
    Activations Density 0.289%

    No Known Activations