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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 122557
    Prev
    Next
    INDEX
    Explanations

    themes related to mind control and manipulation

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

    control, forced, or split personas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    verwijspagina
    -0.65
     disambiguazione
    -0.49
    windowFixed
    -0.48
    TableBody
    -0.45
    gebob
    -0.44
     informée
    -0.43
    Personensuche
    -0.42
    AnchorTagHelper
    -0.40
    awtextra
    -0.40
    المكان
    -0.39
    POSITIVE LOGITS
     leſs
    0.39
     growled
    0.39
     pleaſure
    0.38
    TRAILING
    0.36
    {}/
    0.35
     hemorrhage
    0.35
     LaLiga
    0.35
     defaultstate
    0.34
    enumii
    0.34
    MLLoader
    0.34
    Activations Density 0.040%

    No Known Activations