© 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. 15-GEMMASCOPE-RES-16K
    11. 2625
    Prev
    Next
    INDEX
    Explanations

    HTML and markup-related elements, particularly labels and formatting structures

    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
    ruptedException
    -0.63
     étoit
    -0.62
    )».
    -0.61
    {}/
    -0.61
    )".
    -0.60
    ).}
    -0.60
     zvuky
    -0.59
     maxn
    -0.59
    ;");
    -0.58
     }}$}
    -0.57
    POSITIVE LOGITS
    AsUp
    0.81
    PyExc
    0.71
    WithMany
    0.67
    UnusedPrivate
    0.60
    
    0.59
    存于互联网档案馆
    0.59
     joaat
    0.58
     BrowserModule
    0.58
     BoxFit
    0.57
    mergeFrom
    0.56
    Activations Density 0.636%

    No Known Activations