© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 25-GEMMASCOPE-RES-16K
    6. 9176
    Prev
    Next
    INDEX
    Explanations

    elements related to personal relationships and dynamics among friends

    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
    KURZBESCHREIBUNG
    -0.60
    orr
    -0.53
    risen
    -0.49
    __);
    -0.49
    teries
    -0.49
     KeyError
    -0.49
     ASSOCI
    -0.48
     vuitton
    -0.48
     IndexError
    -0.48
     surla
    -0.48
    POSITIVE LOGITS
     mutual
    0.88
     chemistry
    0.86
     shared
    0.72
    mutual
    0.72
     inseparable
    0.71
     together
    0.71
    Chemistry
    0.70
     compatibility
    0.70
    Mutual
    0.70
     sparks
    0.70
    Activations Density 0.364%

    No Known Activations