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. 8-GEMMASCOPE-RES-16K
    6. 14370
    Prev
    Next
    INDEX
    Explanations

    terms related to specific types of exceptions in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TagMode
    -1.03
    LookAnd
    -0.80
     GenerationType
    -0.72
     typelib
    -0.65
    CloseOperation
    -0.63
     DbType
    -0.63
     AppCompatTheme
    -0.60
     مرئيه
    -0.57
     externi
    -0.56
     ThemeData
    -0.56
    POSITIVE LOGITS
     BitmapFactory
    0.48
    lanti
    0.48
     SafeMath
    0.47
    ruptedException
    0.44
    ariConfig
    0.43
     birlikte
    0.42
    ChildScrollView
    0.42
    WithIOException
    0.42
    Reentrant
    0.41
    ellingham
    0.41
    Activations Density 0.559%

    No Known Activations