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-2-9B
    4. Residual Stream - 16k
    5. 23-GEMMASCOPE-RES-16K
    6. 2464
    Prev
    Next
    INDEX
    Explanations

    elements of programming constructs and syntax in coding

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CloseOperation
    -0.66
    tagHelperRunner
    -0.59
    RectangleBorder
    -0.58
    OGND
    -0.54
    oneofs
    -0.50
     protoimpl
    -0.49
     unknownFields
    -0.49
     NSCoder
    -0.48
     BorderSide
    -0.48
    RTEX
    -0.48
    POSITIVE LOGITS
     contribuir
    0.37
     contributo
    0.36
     contribue
    0.35
    이는
    0.35
     contribu
    0.34
     хора
    0.33
     contributor
    0.33
     contribution
    0.32
     hierbei
    0.32
    icolor
    0.32
    Activations Density 0.304%

    No Known Activations