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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 14956
    Prev
    Next
    INDEX
    Explanations

    code related to APIs and request handling

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

    Tokens preceding names or titles

    np_acts-logits-general · gemini-2.0-flash

    SELECT name

    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
     ?>/
    -0.76
     Wikimedijinoj
    -0.64
    OOTDTY
    -0.62
     nawr
    -0.60
     contextLoads
    -0.60
     LUMP
    -0.59
    الدراسه
    -0.59
     تانيه
    -0.56
     سكانية
    -0.55
    >--}}
    -0.55
    POSITIVE LOGITS
     name
    1.13
    name
    1.01
     Name
    0.92
     title
    0.86
     NAME
    0.86
    Name
    0.83
    title
    0.79
    ชื่อ
    0.75
     Title
    0.72
     nombre
    0.71
    Activations Density 0.768%

    No Known Activations