© 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. 1-GEMMASCOPE-RES-16K
    11. 5864
    Prev
    Next
    INDEX
    Explanations

    repeated references to offenses in legal and sports contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Personendaten
    -0.88
    ">//
    -0.83
    Искәрмәләр
    -0.62
    "}")
    -0.58
     disponibilités
    -0.58
    Tikang
    -0.57
    stdc
    -0.57
    OnTop
    -0.57
     Constraints
    -0.56
     δυνα
    -0.56
    POSITIVE LOGITS
     offense
    1.40
     offence
    1.27
     Offense
    1.05
     offenses
    1.01
     offences
    0.91
     offensive
    0.78
     HQ
    0.78
     offices
    0.73
    offensive
    0.71
     offensi
    0.69
    Activations Density 0.068%

    No Known Activations