© 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. 14-GEMMASCOPE-RES-16K
    11. 7800
    Prev
    Next
    INDEX
    Explanations

    terms related to statistical noise and its effects in data analysis and reconstruction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     entanto
    -0.87
    ifrance
    -0.60
    λοι
    -0.58
     perché
    -0.56
     however
    -0.54
     потому
    -0.51
     perchè
    -0.49
    rawDesc
    -0.48
    however
    -0.48
     deshalb
    -0.47
    POSITIVE LOGITS
     InputDecoration
    0.84
    ViewFeatures
    0.79
    tagHelperRunner
    0.69
    GOTREF
    0.68
    FormTagHelper
    0.66
    migrationBuilder
    0.65
    Atsauces
    0.63
     مرئيه
    0.63
    Ārējās
    0.63
     insuffisamment
    0.61
    Activations Density 0.771%

    No Known Activations