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. 2-GEMMASCOPE-RES-16K
    6. 6574
    Prev
    Next
    INDEX
    Explanations

    elements related to user interface components and event handling in a software context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 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
     typelib
    -0.58
     doubtnut
    -0.54
     convertView
    -0.53
    AutoScaleMode
    -0.52
    QMetaType
    -0.51
    統領
    -0.50
    viewDidLoad
    -0.50
     DOWNVOTE
    -0.50
    DeleteBehavior
    -0.50
     Guilt
    -0.49
    POSITIVE LOGITS
    jLabel
    0.91
    findpost
    0.77
    MessageOf
    0.75
     وتسجيلات
    0.73
    RegressionTest
    0.73
    iastes
    0.71
     Chwiliwch
    0.71
    AndEndTag
    0.71
    UnusedPrivate
    0.69
    TagMode
    0.68
    Activations Density 0.139%

    No Known Activations