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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 3344
    Prev
    Next
    INDEX
    Explanations

    references to printed circuit board (PCB) manufacturing processes and techniques

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Printed circuit boards and soldering

    np_acts-logits-general · gemini-2.0-flash

    printed circuit boards and solder

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    INCREF
    -0.45
    チール
    -0.40
     EconPapers
    -0.39
     power
    -0.38
    RTSC
    -0.36
    LookAnd
    -0.36
     canceling
    -0.35
     contribution
    -0.35
    OGND
    -0.35
    imer
    -0.34
    POSITIVE LOGITS
     soldering
    0.70
     solder
    0.59
    Circuit
    0.58
    styleable
    0.58
     Circuits
    0.56
     soldered
    0.56
     PCB
    0.56
     Circuit
    0.54
     pcb
    0.53
     circuit
    0.53
    Activations Density 0.505%

    No Known Activations