© 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-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 8479
    Prev
    Next
    INDEX
    Explanations

    themes of longing and desire in relationships and aspirations

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

    expressions of desire or wanting something, particularly the phrase "want to" or "wanted to".

    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
     GenerationType
    -0.68
    rungsseite
    -0.57
     FontWeight
    -0.57
    verifyException
    -0.57
     AppComponent
    -0.56
    ロウィン
    -0.55
     createSprite
    -0.54
     AssemblyTitle
    -0.54
     snippetHide
    -0.53
    }}]{
    -0.52
    POSITIVE LOGITS
     glory
    0.58
     freedom
    0.57
     independence
    0.53
     approval
    0.51
     validation
    0.50
     answers
    0.47
     APPROVAL
    0.46
     revenge
    0.46
     fame
    0.45
     access
    0.44
    Activations Density 0.407%

    No Known Activations