© 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. 25-GEMMASCOPE-RES-16K
    6. 772
    Prev
    Next
    INDEX
    Explanations

    specific characters or symbols, particularly certain Thai or Indic characters, and numeric representations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    इटम
    -0.57
    ೕ
    -0.56
     们
    -0.54
    ValueStyle
    -0.53
    học
    -0.52
     חיצוניים
    -0.51
     背影
    -0.51
    ülle
    -0.49
    ázaro
    -0.48
    श्ले
    -0.48
    POSITIVE LOGITS
     Jefus
    0.61
    ſelf
    0.60
     laiton
    0.55
     Theſe
    0.53
     Majefty
    0.51
     myſelf
    0.51
     pleaſure
    0.49
     juſ
    0.49
     greateſt
    0.49
    ſelves
    0.49
    Activations Density 0.005%

    No Known Activations