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. 16-GEMMASCOPE-RES-16K
    6. 16234
    Prev
    Next
    INDEX
    Explanations

    programming language syntax and structure, particularly related to templates, classes, and definitions

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

    C++ code and syntax

    np_acts-logits-general · gemini-2.0-flash

    programming keywords and types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fromnode
    -0.53
    IVEREF
    -0.52
    onViewCreated
    -0.51
    Kariera
    -0.50
    writeFieldEnd
    -0.50
     sobą
    -0.49
    انيف
    -0.49
     avoient
    -0.48
     ?>">
    -0.48
    bootstrapcdn
    -0.47
    POSITIVE LOGITS
     kasarigan
    0.61
    putBoolean
    0.59
    XtraEditors
    0.57
    Gotcha
    0.55
    sina
    0.55
    __(/*!
    0.54
    leno
    0.54
    pexpr
    0.54
    LocalizedString
    0.53
    AndroidJUnit
    0.53
    Activations Density 0.108%

    No Known Activations