© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 5108
    Prev
    Next
    INDEX
    Explanations

    terms related to the development, implementation, and analysis of scientific or technical processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     El
    -0.64
     N
    -0.59
    illa
    -0.57
     Hor
    -0.57
     Az
    -0.57
     
    -0.57
     Pet
    -0.57
    i
    -0.56
     is
    -0.56
     also
    -0.56
    POSITIVE LOGITS
     Monfieur
    1.43
     Theſe
    1.37
     itſelf
    1.35
     myſelf
    1.29
    ſelf
    1.25
     himſelf
    1.23
     Jefus
    1.23
    ſelves
    1.23
     Shakspeare
    1.21
     مشين
    1.20
    Activations Density 0.399%

    No Known Activations