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. 18-GEMMASCOPE-RES-16K
    6. 14567
    Prev
    Next
    INDEX
    Explanations

    various forms of variety and range in both topics and services

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

    "everything" or "everyone" followed by "from"

    np_acts-logits-general · gemini-2.0-flash

    everything from

    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
    tamol
    -0.52
     ausz
    -0.50
    APOLIS
    -0.48
    Autoritní
    -0.48
    rungsseite
    -0.48
     betweenstory
    -0.47
     yeux
    -0.45
    ųjų
    -0.44
     noten
    -0.44
     Défense
    -0.43
    POSITIVE LOGITS
     ranging
    1.76
     from
    1.50
     desde
    1.38
    ranging
    1.33
     From
    1.24
    从
    1.19
    desde
    1.17
    from
    1.17
     từ
    1.17
     allant
    1.16
    Activations Density 0.240%

    No Known Activations