© 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-2-9B
    4. Residual Stream - 16k
    5. 38-GEMMASCOPE-RES-16K
    6. 10282
    Prev
    Next
    INDEX
    Explanations

    discussions about the importance of community and social connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enumi
    -0.42
    既
    -0.41
    both
    -0.40
     both
    -0.40
     particuli
    -0.39
     muualla
    -0.38
     MainAxisSize
    -0.38
     både
    -0.38
     other
    -0.38
    ::*;
    -0.37
    POSITIVE LOGITS
     yet
    0.84
    yet
    0.71
     influential
    0.65
     informative
    0.65
     oftentimes
    0.63
    Yet
    0.63
     impactful
    0.63
     profitable
    0.61
     purposeful
    0.60
     insightful
    0.59
    Activations Density 0.320%

    No Known Activations