© 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. 4816
    Prev
    Next
    INDEX
    Explanations

    elements related to relationships and significance in texts

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

    Follows punctuation, "that", or words like "protected" or "evidence."

    np_acts-logits-general · gemini-2.0-flash

    third-person male pronouns

    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
    OLVED
    -0.66
    tonode
    -0.62
    geführten
    -0.60
    webElementXpaths
    -0.59
    ={({
    -0.59
    loyees
    -0.59
    ecution
    -0.59
    OCCURRED
    -0.58
    \]
    -0.58
    gnition
    -0.58
    POSITIVE LOGITS
     him
    1.33
    彼は
    1.06
    him
    1.03
     beliau
    0.87
     egli
    0.86
     lui
    0.86
    彼が
    0.84
     he
    0.83
     그는
    0.83
     él
    0.79
    Activations Density 1.110%

    No Known Activations