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. 19-GEMMASCOPE-RES-16K
    6. 15794
    Prev
    Next
    INDEX
    Explanations

    phrases that emphasize the act of avoiding or refraining from certain actions or situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/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.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fær
    -0.56
    GroupLayout
    -0.54
     ferdig
    -0.53
    licenses
    -0.53
     ChromeDriver
    -0.52
     vertes
    -0.52
     فريبيس
    -0.52
     tikai
    -0.52
     dalamnya
    -0.52
    ouder
    -0.51
    POSITIVE LOGITS
     unnecessary
    0.82
    noinspection
    0.70
     defaultstate
    0.70
    Portály
    0.68
     needless
    0.68
     repetition
    0.68
    loài
    0.67
     Potential
    0.65
    دانشنامهٔ
    0.64
     pitfalls
    0.64
    Activations Density 0.144%

    No Known Activations