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. 18-GEMMASCOPE-RES-16K
    6. 603
    Prev
    Next
    INDEX
    Explanations

    elements in a programming context, specifically related to PHP and HTML

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

    Code snippets or programming syntax

    np_acts-logits-general · gemini-2.0-flash

    code snippets and templating

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SequentialGroup
    -0.56
     '\\;'
    -0.53
    entibus
    -0.51
     capables
    -0.46
    <eos>
    -0.44
    ypus
    -0.41
     mukana
    -0.40
    ↵↵
    -0.40
     violenza
    -0.39
     negociaciones
    -0.39
    POSITIVE LOGITS
    ftagPool
    0.89
     kasarigan
    0.89
     Савезне
    0.85
     समीक्षक
    0.76
    WireFormatLite
    0.76
     "..\..\..\
    0.76
    CppMethod
    0.75
     Wikimedijinoj
    0.73
    thâu
    0.73
    yntaxException
    0.73
    Activations Density 0.041%

    No Known Activations