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-2-2B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 15232
    Prev
    Next
    INDEX
    Explanations

    discussions around authority and permission in the context of events or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 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
    Personensuche
    -0.62
    ovatel
    -0.58
     iirc
    -0.53
     fairly
    -0.52
    Specifically
    -0.50
     ect
    -0.48
     Mostly
    -0.48
     sorta
    -0.48
     довольно
    -0.48
     pretty
    -0.48
    POSITIVE LOGITS
     shameless
    0.78
     democracy
    0.76
     politicians
    0.74
     hypocrisy
    0.72
     corruption
    0.71
     hypocrite
    0.70
     shameful
    0.69
     fools
    0.69
     impunity
    0.68
    onsense
    0.68
    Activations Density 0.292%

    No Known Activations