© 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. 22-GEMMASCOPE-RES-16K
    11. 11424
    Prev
    Next
    INDEX
    Explanations

    instances of abusive or threatening behavior

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

    Offensive or abusive language

    np_acts-logits-general · gemini-2.0-flash

    personal attacks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     发表于
    -0.58
     parad
    -0.57
    __':
    -0.57
    coltà
    -0.56
     Voluntary
    -0.53
    []
    -0.52
     preved
    -0.51
     Italijanski
    -0.51
     panik
    -0.51
    ύπ
    -0.51
    POSITIVE LOGITS
     insults
    1.30
     harassment
    1.20
     insulting
    1.17
     insult
    1.13
     bullying
    1.06
     insulted
    1.05
     harassing
    0.96
     tau
    0.95
     threats
    0.94
     attacks
    0.94
    Activations Density 0.465%

    No Known Activations