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. 15015
    Prev
    Next
    INDEX
    Explanations

    code-related terminology and class structures in programming languages

    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
    حوالہ
    -0.61
    (!__
    -0.55
    WithIOException
    -0.53
    _))
    -0.50
    ")));
    
    -0.49
    WriteTagHelper
    -0.49
     externi
    -0.49
    unistd
    -0.48
    AddTagHelper
    -0.48
    -------------</
    -0.48
    POSITIVE LOGITS
     MainAxisSize
    0.75
     المعيارى
    0.71
     eduardo
    0.67
    ::
    0.64
     Efq
    0.61
     Adnan
    0.59
     Monfieur
    0.59
     crdi
    0.58
     doraemon
    0.56
     समीक्षाओं
    0.56
    Activations Density 0.821%

    No Known Activations