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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 24-GEMMASCOPE-RES-16K
    6. 4727
    Prev
    Next
    INDEX
    Explanations

    phrases and concepts related to complex numerical data and parameters, often within technical or scientific contexts

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

    Code, math, or equations

    np_acts-logits-general · gemini-2.0-flash

    .

    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
    Personendaten
    -0.98
    expandindo
    -0.96
    )』
    -0.91
    )*/
    -0.84
    =[]
    
    -0.77
    تقاوى
    -0.76
    )");
    
    -0.72
    )]
    
    -0.71
    ")]
    
    -0.70
     """
    
    -0.69
    POSITIVE LOGITS
    …
    3.07
    ...
    3.05
     ...
    3.00
     …
    2.90
    ….
    2.79
    ....
    2.77
    ……
    2.70
    …..
    2.68
     ....
    2.64
    .....
    2.62
    Activations Density 1.508%

    No Known Activations