© 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-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 34995
    Prev
    Next
    INDEX
    Explanations

    references to a specific individual named Robins and variations of that name within a contextual framework

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

    rob followed by ins

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    />";
    -0.44
     InputDecoration
    -0.42
     Autorizaciones
    -0.41
    yscale
    -0.38
    detectChanges
    -0.38
     companyId
    -0.37
    Xaml
    -0.35
     mei
    -0.35
     linkovi
    -0.35
    eya
    -0.34
    POSITIVE LOGITS
    rob
    2.27
     rob
    2.16
    Rob
    1.97
     Rob
    1.90
     ROB
    1.85
    ROB
    1.84
     robber
    1.58
     robbed
    1.55
     robbing
    1.53
     Robins
    1.52
    Activations Density 0.023%

    No Known Activations