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. 5411
    Prev
    Next
    INDEX
    Explanations

    phrases related to the impact and contributions of individuals within a community

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

    Following personal pronouns

    np_acts-logits-general · gemini-2.0-flash

    how things are done

    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
     للمعارف
    -0.88
     resourceCulture
    -0.74
     initComponents
    -0.72
    bootstrapcdn
    -0.70
    AutoField
    -0.70
     Wicidata
    -0.66
    ostante
    -0.65
    WarningLevel
    -0.65
    addPreferredGap
    -0.64
    GroupLayout
    -0.63
    POSITIVE LOGITS
     essentially
    1.03
     indirectly
    1.03
     effectively
    1.01
     Essentially
    0.90
    Essentially
    0.89
    essentially
    0.86
    effectively
    0.83
     Effectively
    0.82
    indirect
    0.81
     indirec
    0.81
    Activations Density 0.519%

    No Known Activations