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. 16-GEMMASCOPE-RES-16K
    6. 3190
    Prev
    Next
    INDEX
    Explanations

    the presence of structured data entries and metadata formatting

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

    Code snippets or XML-like structures

    np_acts-logits-general · gemini-2.0-flash

    reading or writing file data

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    subequations
    -0.48
    CodeDom
    -0.47
     male
    -0.45
    WarningLevel
    -0.44
    JsonValue
    -0.43
    moveToFirst
    -0.43
     Cal
    -0.42
     راه
    -0.42
     giáo
    -0.42
    лық
    -0.41
    POSITIVE LOGITS
     écoulé
    0.71
    tagHelperRunner
    0.63
     chunk
    0.62
     chunks
    0.62
     chun
    0.61
     lengths
    0.60
    tôi
    0.59
     Италијани
    0.59
     Combien
    0.59
     Length
    0.58
    Activations Density 0.565%

    No Known Activations