© 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. 1-GEMMASCOPE-RES-16K
    6. 13229
    Prev
    Next
    INDEX
    Explanations

    terms related to biological or bioengineering contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SpringRunner
    -0.61
    AndEndTag
    -0.60
     popolare
    -0.51
    Gweler
    -0.49
     dàng
    -0.48
     beren
    -0.48
    hoeddwyd
    -0.48
    τουργ
    -0.47
    IUrlHelper
    -0.47
    WebControls
    -0.47
    POSITIVE LOGITS
     bio
    5.13
     Bio
    4.63
    Bio
    4.38
    bio
    4.32
     BIO
    3.54
    BIO
    3.33
     био
    3.22
     bios
    2.75
    生物
    2.49
     Bios
    2.38
    Activations Density 0.088%

    No Known Activations