© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 15460
    Prev
    Next
    INDEX
    Explanations

    references to programming-related terms and potential vulnerabilities, particularly in the context of buffer overflows and memory management

    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
     gynhyrchwyd
    -0.80
     Marcell
    -0.75
    oughby
    -0.75
     Hodges
    -0.74
     Inscrivez
    -0.73
     Metzger
    -0.73
     Theſe
    -0.73
     Bangor
    -0.71
     Agr
    -0.70
     userDetails
    -0.69
    POSITIVE LOGITS
     CWE
    0.84
    CWE
    0.83
     Carroll
    0.79
    SPATH
    0.78
    viewDidLoad
    0.74
    URIComponent
    0.73
    Roe
    0.72
     Krieg
    0.72
     Roe
    0.72
     AssemblyCulture
    0.70
    Activations Density 7.822%

    No Known Activations