Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 14121
    Prev
    Next
    INDEX
    Explanations

    phrases that discuss the impossibility or challenge of achieving something

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

    German words/phrases

    np_acts-logits-general · gemini-2.0-flash

    German medical and technical terms

    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
     resourceCulture
    -0.66
     disambiguazione
    -0.63
     كومونز
    -0.63
    ChromeDriver
    -0.59
     transférez
    -0.55
    ViewImports
    -0.54
    ########.
    -0.53
    ImageField
    -0.53
     joaat
    -0.52
     विश्वसनीयता
    -0.51
    POSITIVE LOGITS
     anz
    0.60
    itology
    0.54
     Coming
    0.53
     going
    0.53
     Occur
    0.52
     COMING
    0.51
     occurring
    0.51
     anzu
    0.50
     aanwezig
    0.50
     Going
    0.49
    Activations Density 0.052%

    No Known Activations