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. 10-GEMMASCOPE-RES-16K
    6. 11809
    Prev
    Next
    INDEX
    Explanations

    references to free services or products

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rungsseite
    -1.15
     متعلقه
    -1.12
     pinulongan
    -1.09
     AssemblyTitle
    -0.97
    Personendaten
    -0.97
    Personensuche
    -0.89
    )*/
    -0.88
     Италијани
    -0.88
     Metacritic
    -0.87
    expandindo
    -0.86
    POSITIVE LOGITS
     Free
    1.64
     free
    1.52
    Free
    1.51
     FREE
    1.42
    FREE
    1.40
    free
    1.37
     frees
    1.14
     Freeport
    1.10
     libre
    1.08
     FRE
    1.03
    Activations Density 0.055%

    No Known Activations