© 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-2-2B
    7. Residual Stream - 16k
    9. 12-GEMMASCOPE-RES-16K
    11. 15017
    Prev
    Next
    INDEX
    Explanations

    expressions of honesty or frankness in opinions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aguya
    -0.71
    GEBURTS
    -0.65
    ódź
    -0.64
    ouncil
    -0.63
     pach
    -0.62
    americas
    -0.61
    :✨
    -0.60
    lemmer
    -0.60
    =’
    -0.59
    archiviato
    -0.59
    POSITIVE LOGITS
     honestly
    1.00
     frankly
    0.97
    Honestly
    0.94
    Frankly
    0.93
     Honestly
    0.90
    honestly
    0.84
     tbh
    0.70
     honest
    0.70
    ScopeManager
    0.69
     honn
    0.68
    Activations Density 0.099%

    No Known Activations