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. 20-GEMMASCOPE-RES-16K
    6. 14800
    Prev
    Next
    INDEX
    Explanations

    time-related measurements and references

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

    Time duration: "hour" or "year" before "ago"

    np_acts-logits-general · gemini-2.0-flash

    time measured in hours or years ago

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    endphp
    -0.91
    ⓧ
    -0.76
    /**
    -0.75
    GEBURTSDATUM
    -0.75
    
    -0.69
    artifactId
    -0.67
     "..\..\
    -0.64
    /***/
    -0.64
    lamabad
    -0.64
    uxxxx
    -0.64
    POSITIVE LOGITS
    long
    0.65
    ين
    0.52
     inteiro
    0.52
     each
    0.52
     każ
    0.51
    ıy
    0.50
     houſe
    0.49
    teen
    0.48
     fifty
    0.48
    gın
    0.47
    Activations Density 0.129%

    No Known Activations