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. 14-GEMMASCOPE-RES-16K
    6. 3094
    Prev
    Next
    INDEX
    Explanations

    the presence and close of code blocks or functions in programming syntax

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    saraba
    -0.53
    ående
    -0.53
    loroethene
    -0.51
    ropo
    -0.50
    AddField
    -0.50
    częściej
    -0.49
     يتيمه
    -0.49
    ngrx
    -0.48
     propOrder
    -0.48
     Dentro
    -0.48
    POSITIVE LOGITS
    SourceChecksum
    0.69
    HasColumnType
    0.63
    RunAsync
    0.55
     Quark
    0.52
     ProtoMessage
    0.51
     NSCoder
    0.51
    #
    0.50
    webElementXpaths
    0.50
    bootstrapcdn
    0.50
    SerializedName
    0.49
    Activations Density 0.089%

    No Known Activations