Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 12035
    Prev
    Next
    INDEX
    Explanations

    themes related to authority and obedience within hierarchical structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     funds
    -0.38
    ]=-
    -0.35
     ανά
    -0.35
     zuständig
    -0.33
    []"
    -0.33
     fiches
    -0.31
    UAGE
    -0.31
    igung
    -0.31
    )=-
    -0.31
    Counters
    -0.30
    POSITIVE LOGITS
     obedient
    0.68
     obedience
    0.66
    ImageContext
    0.63
     willingly
    0.63
     unquestion
    0.62
     acquies
    0.59
     blindly
    0.58
     Obedience
    0.56
     unconditionally
    0.55
     ivelany
    0.54
    Activations Density 0.440%

    No Known Activations