© 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. 2-GEMMASCOPE-RES-16K
    6. 3524
    Prev
    Next
    INDEX
    Explanations

    references to structured data elements in a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enumi
    -0.95
    ValueStyle
    -0.88
    knię
    -0.75
    homonymie
    -0.74
     Efq
    -0.70
     ujednoznacz
    -0.68
     Reſ
    -0.67
    LEGGI
    -0.65
     وتسجيلات
    -0.65
     Coates
    -0.64
    POSITIVE LOGITS
    ″
    1.11
    ′
    1.06
    ](
    0.85
    :@"
    0.76
    ′,
    0.71
    ","
    0.69
    )](
    0.68
    ":"
    0.65
    "](
    0.65
    ','
    0.64
    Activations Density 0.140%

    No Known Activations