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. 2-GEMMASCOPE-RES-16K
    6. 4456
    Prev
    Next
    INDEX
    Explanations

    terms associated with technical specifications and document formatting

    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
     AttributeSet
    -0.69
     незавершена
    -0.60
    تقاوى
    -0.59
     HasFactory
    -0.57
    BASEPATH
    -0.57
    原始内容存档于
    -0.56
    Enllaces
    -0.56
    vode
    -0.55
     BoxFit
    -0.55
    MigrationBuilder
    -0.54
    POSITIVE LOGITS
     vis
    0.66
    Vis
    0.66
     Vis
    0.62
    vis
    0.62
    documentclass
    0.56
    AddWithValue
    0.53
    Metro
    0.49
     harness
    0.48
    (';
    0.47
     Metro
    0.47
    Activations Density 2.874%

    No Known Activations