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. 6-GEMMASCOPE-RES-16K
    6. 13336
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and variables relating to physical equations or theories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/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.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    évaluateur
    -0.55
     getArguments
    -0.55
    SuccessListener
    -0.52
     eri
    -0.49
     pomy
    -0.47
     peine
    -0.47
    ूम
    -0.47
     EconPapers
    -0.46
    })->
    -0.46
     Igual
    -0.46
    POSITIVE LOGITS
     Roskov
    0.71
    __':
    
    0.70
    __':
    0.65
     doInBackground
    0.65
    rungsseite
    0.60
     SafeMath
    0.60
    TypedDataSet
    0.60
    WebServlet
    0.58
    setVerticalGroup
    0.55
     vPvB
    0.55
    Activations Density 1.828%

    No Known Activations