Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 10369
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to precision and careful execution

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

    Adverbs ending in "-ly"

    np_acts-logits-general · gemini-2.0-flash

    adverbs modifying verbs or adjectives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    StoryboardSegue
    -0.89
    "},
    
    -0.89
    }`).
    -0.85
    "],
    
    -0.83
    "])
    
    -0.81
    "]
    
    -0.81
    '}>
    -0.79
     ]
    
    -0.77
    ")));
    
    -0.75
    "]));
    -0.75
    POSITIVE LOGITS
     enough
    0.89
    enough
    0.79
     demais
    0.74
     ביותר
    0.70
     indeed
    0.68
     ENOUGH
    0.66
    Enough
    0.65
    ly
    0.65
     רבה
    0.63
    zeitig
    0.62
    Activations Density 0.402%

    No Known Activations