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. 2-GEMMASCOPE-RES-16K
    6. 13058
    Prev
    Next
    INDEX
    Explanations

    instantiations or creations of objects in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SourceChecksum
    -0.59
    səhifə
    -0.59
    addPreferredGap
    -0.56
    TagMode
    -0.56
    elemField
    -0.55
    errHandler
    -0.54
    UIFont
    -0.53
    mobileqq
    -0.53
     يتيمه
    -0.52
    matchCondition
    -0.52
    POSITIVE LOGITS
    ArgsConstructor
    0.52
    writerow
    0.48
     HasFactory
    0.46
    __(
    0.42
     initComponents
    0.40
     rip
    0.40
    constructor
    0.36
    toEqual
    0.36
    ContentView
    0.35
    createServer
    0.34
    Activations Density 0.273%

    No Known Activations