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. 9-GEMMASCOPE-RES-16K
    6. 15891
    Prev
    Next
    INDEX
    Explanations

    web addresses or links

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/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.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     in
    -0.59
    ни
    -0.59
     
    -0.57
     a
    -0.57
     as
    -0.56
    */
    
    -0.56
    0
    -0.56
    5
    -0.55
     even
    -0.53
    1
    -0.52
    POSITIVE LOGITS
     ErrIntOverflow
    1.18
    WriteTagHelper
    1.10
     doInBackground
    1.09
     WWW
    1.07
     pinulongan
    1.06
     Paglinawan
    1.05
     ddelweddau
    1.03
    Sucesor
    1.00
     contextLoads
    0.99
     ſche
    0.96
    Activations Density 0.026%

    No Known Activations