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. 15-GEMMASCOPE-RES-16K
    6. 5257
    Prev
    Next
    INDEX
    Explanations

    topics related to technology and innovation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/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.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    __))
    -0.72
    
    -0.70
    iented
    -0.68
    WebElementEntity
    -0.68
     unknownFields
    -0.66
    orari
    -0.65
     CreateTagHelper
    -0.65
     Forumite
    -0.64
    WriteTagHelper
    -0.63
     дописавши
    -0.63
    POSITIVE LOGITS
     is
    0.66
     means
    0.63
     would
    0.63
     isn
    0.60
    Šaltiniai
    0.57
     allows
    0.51
     wasn
    0.51
     can
    0.48
     wouldn
    0.47
    では
    0.46
    Activations Density 0.447%

    No Known Activations