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. 11-GEMMASCOPE-RES-16K
    6. 1949
    Prev
    Next
    INDEX
    Explanations

    the presence of mentions or references to specific entities or subjects in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     متعلقه
    -0.92
     betweenstory
    -0.76
     ""],
    -0.72
    __*/
    -0.71
    RegressionTest
    -0.67
    CppCodeGen
    -0.67
    AccessorTable
    -0.66
     الحره
    -0.62
     modelAndView
    -0.62
    "]);
    
    -0.62
    POSITIVE LOGITS
     scolaires
    0.75
     enough
    0.66
    enough
    0.66
     demais
    0.63
     envers
    0.59
     hiér
    0.58
     nicio
    0.58
     klubben
    0.57
     znaczy
    0.57
     étrangères
    0.56
    Activations Density 0.421%

    No Known Activations