Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 4-GEMMASCOPE-RES-16K
    6. 15964
    Prev
    Next
    INDEX
    Explanations

    terms related to legal proceedings that are ongoing or awaiting resolution

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    matchCondition
    -0.58
     ContentValues
    -0.54
    typeorm
    -0.51
     pageContext
    -0.50
    ContentValues
    -0.50
     Wikimédia
    -0.48
    phosa
    -0.47
    photobucket
    -0.46
    >");
    
    -0.46
    〗
    -0.45
    POSITIVE LOGITS
     pending
    1.70
    pending
    1.44
     Pending
    1.39
    Pending
    1.38
    ongoing
    1.35
     ongoing
    1.34
    PENDING
    1.31
    Ongoing
    1.24
     Ongoing
    1.22
     underway
    1.17
    Activations Density 0.388%

    No Known Activations