© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 3330
    Prev
    Next
    INDEX
    Explanations

    names of individuals associated with specific professions or notable actions

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

    birth or graduation

    np_acts-logits-general · gemini-2.0-flash

    born and early life context

    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
    UserScript
    -0.60
    GraphicsUnit
    -0.57
    Enllaces
    -0.57
    apimachinery
    -0.55
    ritsar
    -0.53
     Ramadan
    -0.52
     Extinction
    -0.51
    +#+#
    -0.51
     extinct
    -0.50
    Kjelder
    -0.50
    POSITIVE LOGITS
     Born
    1.00
     childhood
    0.96
    Born
    0.94
     born
    0.94
     Childhood
    0.89
    Childhood
    0.85
    Originally
    0.83
     awalnya
    0.82
     enfance
    0.79
     >=",
    0.79
    Activations Density 0.317%

    No Known Activations