© 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. 2-GEMMASCOPE-RES-16K
    6. 6107
    Prev
    Next
    INDEX
    Explanations

    references to individuals previously holding a position or title

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    migrationBuilder
    -0.69
    HasAnnotation
    -0.58
     Вікіпе
    -0.57
     încă
    -0.55
    andExpect
    -0.54
    لينكات
    -0.53
    irchen
    -0.53
     Angio
    -0.53
     μά
    -0.52
     sposa
    -0.52
    POSITIVE LOGITS
     former
    3.44
    Former
    3.27
     Former
    3.23
    former
    3.05
     ehemaligen
    2.36
     ehemalige
    2.31
     ehemal
    2.07
     mantan
    2.03
     formerly
    1.89
     býval
    1.89
    Activations Density 0.053%

    No Known Activations