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. 2169
    Prev
    Next
    INDEX
    Explanations

    terms related to difficulties and challenges encountered in various 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
     snippetHide
    -0.54
    JspWriter
    -0.49
    leté
    -0.47
    └──
    -0.45
    czka
    -0.43
     незавершена
    -0.43
    今度
    -0.41
     BoxDecoration
    -0.41
    inkscape
    -0.40
    windowFixed
    -0.40
    POSITIVE LOGITS
     initially
    3.21
     initial
    2.79
     Initially
    2.76
    Initially
    2.66
     inicialmente
    2.61
     anfangs
    2.52
     iniz
    2.45
    initial
    2.40
    Initial
    2.36
     Initial
    2.28
    Activations Density 0.652%

    No Known Activations