© 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. 2-GEMMASCOPE-RES-16K
    6. 6499
    Prev
    Next
    INDEX
    Explanations

    specific named entities, including proper nouns and technical terms across various contexts

    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
     '\\;'
    -0.85
    OGND
    -0.82
    })();
    
    -0.78
     تضيفلها
    -0.77
    StoryboardSegue
    -0.76
    Хьажоргаш
    -0.73
    tagHelperRunner
    -0.73
    verwijspagina
    -0.73
    reportWebVitals
    -0.72
     ſhe
    -0.72
    POSITIVE LOGITS
    ha
    1.40
    HA
    0.93
    Ha
    0.80
    haa
    0.72
     Ha
    0.71
     ha
    0.68
    hac
    0.66
    ecore
    0.63
    hā
    0.60
    FromArgb
    0.58
    Activations Density 1.347%

    No Known Activations