Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 11295
    Prev
    Next
    INDEX
    Explanations

    references to guidelines and recommendations related to personal choices and societal topics

    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
     AssemblyProduct
    -0.72
     Familienname
    -0.64
     jScrollPane
    -0.64
     autorytatywna
    -0.63
     SEDS
    -0.58
     nahilalakip
    -0.57
    دانشنامهٔ
    -0.56
    kháu
    -0.55
     ويكيپيديا
    -0.53
    AndEndTag
    -0.53
    POSITIVE LOGITS
     avoid
    1.63
     avoidance
    1.63
     avoided
    1.62
     avoiding
    1.56
    avoid
    1.53
     Avoid
    1.52
    Avoid
    1.51
     avoids
    1.47
     AVOID
    1.47
     refrain
    1.38
    Activations Density 0.716%

    No Known Activations