© 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. 13392
    Prev
    Next
    INDEX
    Explanations

    references to positions, titles, and identifiers in professional and academic contexts

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

    Text preceding "at"

    np_acts-logits-general · gemini-2.0-flash

    at

    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
    At
    -0.88
     At
    -0.85
    AT
    -0.68
    at
    -0.60
     oleh
    -0.56
    OF
    -0.56
     zur
    -0.56
    FROM
    -0.55
    Of
    -0.54
    From
    -0.53
    POSITIVE LOGITS
    MemoryWarning
    0.93
     мәкал
    0.86
    InputTagHelper
    0.80
     defaultstate
    0.76
     CreateTagHelper
    0.72
    }\]
    0.71
    IndentedString
    0.71
     tartalomajánló
    0.70
    openConnection
    0.69
     مرئيه
    0.69
    Activations Density 0.167%

    No Known Activations