© 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. 3-GEMMASCOPE-RES-16K
    6. 8131
    Prev
    Next
    INDEX
    Explanations

    references to different types of immune cells and their functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    farin
    -0.69
     محفوظة
    -0.65
     čier
    -0.64
    CHAS
    -0.63
    ronique
    -0.63
     pleaſure
    -0.60
    ždy
    -0.58
    ,$_
    -0.57
     favourable
    -0.57
     väli
    -0.56
    POSITIVE LOGITS
     cells
    2.38
     Cells
    2.19
     CELLS
    1.97
    cells
    1.89
    Cells
    1.86
     cellules
    1.63
     Zellen
    1.58
     células
    1.49
    ocytes
    1.34
    細胞
    1.31
    Activations Density 0.353%

    No Known Activations