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. 14166
    Prev
    Next
    INDEX
    Explanations

    phrases related to comparisons and classifications involving groups or categories

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

    preceding "directions", "hospitals", or found after "both"

    np_acts-logits-general · gemini-2.0-flash

    both X and Y

    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
     ovunque
    -0.57
     spéciaux
    -0.56
     altrimenti
    -0.55
     banyak
    -0.54
     zelfs
    -0.53
     sonst
    -0.53
     Banyak
    -0.51
     adicionales
    -0.51
     alcun
    -0.51
     supplémentaires
    -0.50
    POSITIVE LOGITS
     single
    0.92
     general
    0.88
     regular
    0.86
     Regular
    0.85
     Standard
    0.82
     residential
    0.82
     Single
    0.81
     basic
    0.79
     Ordinary
    0.79
     heterosexual
    0.79
    Activations Density 1.163%

    No Known Activations