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. 13545
    Prev
    Next
    INDEX
    Explanations

    code-related structures and functions within programming or scripting contexts

    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
    webElementXpaths
    -0.92
    basicConfig
    -0.78
    SourceChecksum
    -0.76
     AssemblyCulture
    -0.75
    Portály
    -0.73
    AddTagHelper
    -0.69
    StreetMap
    -0.67
     mergeFrom
    -0.66
    GEBURTSDATUM
    -0.65
     Dracula
    -0.64
    POSITIVE LOGITS
     født
    0.54
     jäsen
    0.53
    InstanceState
    0.52
     rând
    0.47
     artikke
    0.47
    Casual
    0.46
     <<<<<<<<<<<<<<
    0.45
     maș
    0.45
     huom
    0.45
     BorderSide
    0.45
    Activations Density 0.012%

    No Known Activations