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. 20-GEMMASCOPE-RES-16K
    6. 11787
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to success metrics

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

    "success"

    np_acts-logits-general · gemini-2.0-flash

    successful outcomes

    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
    <>("
    -0.48
    inputData
    -0.47
    parks
    -0.45
    setEditable
    -0.45
     prefer
    -0.44
    ofing
    -0.44
     olvides
    -0.42
     byť
    -0.41
    ization
    -0.41
    ButtonItem
    -0.41
    POSITIVE LOGITS
     成功
    0.94
     SUCCESS
    0.90
     Failures
    0.90
     Success
    0.90
     FAILURE
    0.85
     Failure
    0.83
     failures
    0.81
    failure
    0.80
    mybatisplus
    0.79
    SUCCESS
    0.77
    Activations Density 0.100%

    No Known Activations