© 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. 20-GEMMASCOPE-RES-16K
    6. 15370
    Prev
    Next
    INDEX
    Explanations

    phrases related to positions, roles, and responsibilities, particularly in the context of leadership and professional careers

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

    Prior work or positions held

    np_acts-logits-general · gemini-2.0-flash

    past roles in service

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Datuak
    -0.48
    --){
    -0.48
    原始内容存档于
    -0.47
    得
    -0.46
     /\.
    -0.46
    SizeF
    -0.43
     khắc
    -0.42
     nonatomic
    -0.42
    uxxxx
    -0.42
    ומת
    -0.42
    POSITIVE LOGITS
     serving
    1.43
     serve
    1.31
     served
    1.30
    serving
    1.22
    Serving
    1.20
     serves
    1.19
     Serving
    1.17
     Serve
    1.15
    serve
    1.14
    Serve
    1.11
    Activations Density 0.390%

    No Known Activations