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. 5429
    Prev
    Next
    INDEX
    Explanations

    comparative phrases that highlight differences or contrasts

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

    comparison or difference

    np_acts-logits-general · gemini-2.0-flash

    contrast or comparison

    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
     additional
    -0.49
    ();)
    -0.48
     undetermined
    -0.47
     Empieza
    -0.45
    SequentialGroup
    -0.45
     further
    -0.44
    Specific
    -0.43
     еще
    -0.43
    specific
    -0.43
     furthermore
    -0.43
    POSITIVE LOGITS
     kebanyakan
    1.09
     previous
    1.08
     comparable
    1.06
     counterparts
    1.00
     предыду
    0.98
    previous
    0.94
     plupart
    0.93
     similares
    0.93
     maioria
    0.92
     HasFactory
    0.91
    Activations Density 0.570%

    No Known Activations