© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 15-GEMMASCOPE-RES-16K
    6. 8464
    Prev
    Next
    INDEX
    Explanations

    instances of exceptions related to input/output operations in Java

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/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.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     McQu
    -0.58
     leg
    -0.57
     Wur
    -0.57
    <?
    -0.57
     rest
    -0.57
    ành
    -0.56
    most
    -0.56
    aters
    -0.52
    OrEqual
    -0.52
     Gegenteil
    -0.51
    POSITIVE LOGITS
    IOException
    2.54
     IOException
    1.81
    yntaxException
    1.06
    HostException
    1.03
    JSONException
    1.02
    URLException
    0.98
    SQLException
    0.95
    AccessException
    0.94
    TargetException
    0.92
    RemoteException
    0.91
    Activations Density 0.012%

    No Known Activations