© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 25-GEMMASCOPE-RES-16K
    11. 9929
    Prev
    Next
    INDEX
    Explanations

    elements related to relationships and partnerships, particularly those that signify growth and connection

    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
     GenerationType
    -0.51
     trưng
    -0.48
    वरण
    -0.48
    expandindo
    -0.46
    mopolitan
    -0.46
     صوتيه
    -0.46
     getItemId
    -0.44
    mogorov
    -0.43
     handleMessage
    -0.42
    észet
    -0.42
    POSITIVE LOGITS
     pair
    2.68
     pairs
    2.46
     Pair
    2.35
     duo
    2.32
    pair
    2.29
    Pair
    2.22
     Pairs
    2.18
     pairing
    2.15
     PAIR
    2.13
    pairs
    2.09
    Activations Density 0.996%

    No Known Activations