Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 9643
    Prev
    Next
    INDEX
    Explanations

    instances of code syntax and related programming constructs

    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
    hasMoreElements
    -0.61
     '\\;'
    -0.59
    TagMode
    -0.57
    +#+#
    -0.56
    RTSC
    -0.56
    RTCF
    -0.56
    InteropServices
    -0.54
    KEYCODE
    -0.52
    EndProject
    -0.50
     beden
    -0.50
    POSITIVE LOGITS
    MessageOf
    0.81
    protobuf
    0.80
     jspb
    0.71
    OrBuilder
    0.62
     msglen
    0.60
     eld
    0.57
    protoc
    0.56
    ChildScrollView
    0.55
     picioare
    0.54
     ujednoznacz
    0.53
    Activations Density 0.338%

    No Known Activations