Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 10-GEMMASCOPE-RES-16K
    6. 15686
    Prev
    Next
    INDEX
    Explanations

    exception-related terminology, particularly those associated with error handling and runtime issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ]")]
    -0.86
     виправивши
    -0.79
    awtextra
    -0.74
    centralwidget
    -0.68
    plish
    -0.67
    unately
    -0.67
    andExpect
    -0.67
    — 
    -0.67
    ]='\
    -0.66
    TypedDataSet
    -0.66
    POSITIVE LOGITS
    StateException
    1.14
    PointerException
    1.14
    Exception
    1.05
    ruptedException
    1.04
    ElementException
    1.03
    AccessException
    0.96
    NullException
    0.89
    RuntimeException
    0.88
    FormatException
    0.81
    HostException
    0.77
    Activations Density 0.041%

    No Known Activations