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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 6843
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to belonging and social relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    words with the prefix or substring "co" indicating co-occurrence, collaboration, or concurrent relationships.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     yourself
    -0.54
     ourselves
    -0.54
     PeEnEo
    -0.51
    +#+#
    -0.50
     himself
    -0.49
    されていない
    -0.48
    DECREF
    -0.48
     őket
    -0.47
    yourself
    -0.47
     onore
    -0.47
    POSITIVE LOGITS
     nakalista
    0.59
    ing
    0.49
     يتيمه
    0.48
    Referencie
    0.45
     AssemblyTitle
    0.44
     useAppContext
    0.43
    ating
    0.42
     GenerationType
    0.40
    printStackTrace
    0.39
    DockStyle
    0.38
    Activations Density 0.207%

    No Known Activations