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. 16-GEMMASCOPE-RES-16K
    6. 14855
    Prev
    Next
    INDEX
    Explanations

    discourse focused on social justice and inequality

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

    Follows a period in certain writing styles

    np_acts-logits-general · gemini-2.0-flash

    settled into a feeling of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     PLEASE
    -0.53
     please
    -0.52
     usually
    -0.51
    ftal
    -0.51
     several
    -0.51
     übrigens
    -0.51
     cost
    -0.50
     specialty
    -0.49
     last
    -0.49
    you
    -0.49
    POSITIVE LOGITS
    setVerticalGroup
    0.79
     Thus
    0.79
     Hence
    0.77
    Thus
    0.76
     Accordingly
    0.76
    Hence
    0.74
    таратура
    0.72
     newOwner
    0.72
     accordingly
    0.70
    Consequently
    0.70
    Activations Density 0.575%

    No Known Activations