© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 1940
    Prev
    Next
    INDEX
    Explanations

    references to ratios or comparisons in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     incub
    -0.61
    émoc
    -0.60
     incubation
    -0.55
     imgs
    -0.55
    encers
    -0.54
    adomo
    -0.54
     Zorn
    -0.52
    akhstan
    -0.52
     Arlene
    -0.51
     nakalista
    -0.51
    POSITIVE LOGITS
    GetMapping
    0.93
     satisfy
    0.81
    suited
    0.79
     suit
    0.79
     strangers
    0.78
     suits
    0.76
    webElementXpaths
    0.73
     Suit
    0.72
     CommandType
    0.69
     satisfies
    0.69
    Activations Density 0.109%

    No Known Activations