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. 3-GEMMASCOPE-RES-16K
    6. 16140
    Prev
    Next
    INDEX
    Explanations

    references to follow-up actions or processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TagMode
    -0.53
    NgModule
    -0.51
     TextInputType
    -0.51
    clectic
    -0.49
     makeStyles
    -0.48
     lí
    -0.48
     betale
    -0.48
    Rough
    -0.47
     strøm
    -0.47
     CURLOPT
    -0.47
    POSITIVE LOGITS
     followup
    1.19
    脚注の使い方
    0.79
     sequels
    0.73
     betweenstory
    0.70
     sequel
    0.69
    Begriffsklä
    0.69
    /*
    0.66
     >=",
    0.66
     prequel
    0.66
    后续
    0.65
    Activations Density 0.228%

    No Known Activations