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. 21-GEMMASCOPE-RES-16K
    6. 1898
    Prev
    Next
    INDEX
    Explanations

    specific time or date indicators in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     grecque
    -0.57
     ferdig
    -0.51
    setPreferred
    -0.51
    openzeppelin
    -0.51
     culturelle
    -0.50
     Mondiale
    -0.49
     juridique
    -0.47
     truthfully
    -0.46
     върху
    -0.46
     russes
    -0.46
    POSITIVE LOGITS
    ContentAsync
    0.66
     PM
    0.64
     MenuView
    0.63
     Audiodateien
    0.59
     CreateTagHelper
    0.58
    évaluateur
    0.58
    Datuak
    0.58
     pm
    0.57
    hyrchwyd
    0.55
     AM
    0.55
    Activations Density 0.071%

    No Known Activations