© 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. 5-GEMMASCOPE-RES-16K
    6. 7769
    Prev
    Next
    INDEX
    Explanations

    keywords and functions related to event handling and iteration in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GraphicsUnit
    -1.05
    rrggbb
    -0.93
     <=",
    -0.88
     propOrder
    -0.81
    ParallelGroup
    -0.81
    VolleyError
    -0.80
    Portály
    -0.79
    GOTREF
    -0.79
     CreateTagHelper
    -0.79
    extAlignment
    -0.78
    POSITIVE LOGITS
     Dispose
    1.30
    Dispose
    1.25
    disposing
    1.15
    Iterator
    0.78
    dispose
    0.77
    BeginInit
    0.73
     dispose
    0.67
    StartTag
    0.66
    iterator
    0.60
    Disposed
    0.59
    Activations Density 0.028%

    No Known Activations