© 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. 24-GEMMASCOPE-RES-16K
    11. 8519
    Prev
    Next
    INDEX
    Explanations

    elements related to error handling and alerts in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Objective-C code snippets

    np_acts-logits-general · gemini-2.0-flash

    Objective-C methods

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    -0.53
    ErrUnexpectedEOF
    -0.51
    PreferredItem
    -0.51
     européenne
    -0.49
    ürn
    -0.49
     Allowance
    -0.48
     Compl
    -0.48
    しき
    -0.46
     Temps
    -0.46
     EClass
    -0.46
    POSITIVE LOGITS
    
    0.81
    Tikang
    0.71
     perform
    0.55
    tagHelperRunner
    0.52
    ,’”
    0.51
     become
    0.51
     Yamato
    0.50
    ],'
    0.50
    ),”
    0.49
    mares
    0.49
    Activations Density 0.162%

    No Known Activations