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. 23-GEMMASCOPE-RES-16K
    6. 5746
    Prev
    Next
    INDEX
    Explanations

    attributes related to condition and quality assessments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     '*':
    -0.90
    ​—
    -0.87
     NDEBUG
    -0.84
     '-':
    -0.83
    الحياه
    -0.80
     imidlertid
    -0.79
     ―――――
    -0.78
     [],
    
    -0.76
     freilich
    -0.74
     ſind
    -0.73
    POSITIVE LOGITS
     ect
    0.95
     aswell
    0.88
     alot
    0.83
     thats
    0.79
     etc
    0.77
     haha
    0.77
     atleast
    0.67
     &
    0.67
     INCLUDING
    0.67
     BUT
    0.66
    Activations Density 0.993%

    No Known Activations