© 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. 10-GEMMASCOPE-RES-16K
    6. 4312
    Prev
    Next
    INDEX
    Explanations

    mathematical functions and statistical terms

    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
    writeFieldEnd
    -0.64
    yntaxException
    -0.57
    ///</
    -0.55
    ejs
    -0.55
    antMatchers
    -0.50
    帖最后由
    -0.49
     biologique
    -0.49
     appunto
    -0.48
    égard
    -0.48
    atisk
    -0.48
    POSITIVE LOGITS
    XmlAccessType
    0.76
    ftagPool
    0.66
     AssemblyCompany
    0.62
    ExtendWith
    0.58
    Demografia
    0.55
    ########.
    0.51
     kys
    0.50
     alg
    0.49
     Đồng
    0.49
     Citizenship
    0.49
    Activations Density 2.072%

    No Known Activations