© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 9233
    Prev
    Next
    INDEX
    Explanations

    data structures and their attributes

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

    Followed by a comma and a description

    np_acts-logits-general · gemini-2.0-flash

    field identifier names

    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
    .
    -0.55
     makes
    -0.49
    <eos>
    -0.49
     ke
    -0.49
     new
    -0.49
    :
    -0.48
    ikov
    -0.48
     Try
    -0.48
     ma
    -0.47
    bar
    -0.46
    POSITIVE LOGITS
    SourceChecksum
    1.12
    principalColumn
    1.04
    __':
    1.04
    ValueStyle
    1.01
    webElementXpaths
    0.99
     EconPapers
    0.98
     الرياضيه
    0.98
     متعلقه
    0.97
    SequentialGroup
    0.97
    Jeografia
    0.95
    Activations Density 0.110%

    No Known Activations