© 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. 18-GEMMASCOPE-RES-16K
    11. 1734
    Prev
    Next
    INDEX
    Explanations

    terms related to specialized fields, particularly in philosophy and neurology

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

    following sports or sport

    np_acts-logits-general · gemini-2.0-flash

    Olympic sport

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     correctes
    -0.51
    لسط
    -0.51
    nsf
    -0.50
    ListNode
    -0.49
    AxisAlignment
    -0.49
    gaande
    -0.46
     Design
    -0.46
    ECON
    -0.46
    ALE
    -0.46
     campan
    -0.45
    POSITIVE LOGITS
     sport
    1.01
     disciplines
    0.82
     genres
    0.82
     discipline
    0.74
     genre
    0.73
     esporte
    0.72
     môn
    0.72
    sport
    0.71
    Sport
    0.69
     disciplina
    0.68
    Activations Density 0.290%

    No Known Activations