© 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. 1-GEMMASCOPE-RES-16K
    6. 13901
    Prev
    Next
    INDEX
    Explanations

    references to a specific individual named Eric, particularly in relation to legal or notable contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MessageOf
    -0.73
    Enllaces
    -0.68
     GLFW
    -0.66
    VersionUID
    -0.66
    casian
    -0.62
     Kev
    -0.62
    WindowConstants
    -0.62
    Belo
    -0.61
    toHaveBeenCalled
    -0.61
    WriteTagHelper
    -0.61
    POSITIVE LOGITS
     prosecution
    1.03
     Thailand
    0.76
    cls
    0.75
     Prosecution
    0.75
     prosecutor
    0.74
    Eric
    0.72
     Eric
    0.72
    CG
    0.69
     prosecutions
    0.68
    Prosecutors
    0.67
    Activations Density 0.059%

    No Known Activations