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. 11-GEMMASCOPE-RES-16K
    6. 13032
    Prev
    Next
    INDEX
    Explanations

    words related to safety and protection measures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    classmethod
    -0.65
    ItemBackground
    -0.60
    Jeografia
    -0.53
    NullCheck
    -0.51
     linkovi
    -0.50
    HtmlAttribute
    -0.49
    pired
    -0.48
     endforeach
    -0.48
    onViewCreated
    -0.47
     fırs
    -0.47
    POSITIVE LOGITS
     enclosure
    0.74
    MessageTagHelper
    0.70
     Enclosure
    0.69
     enclose
    0.67
    MENAFN
    0.65
     enclosing
    0.64
     Confidentiality
    0.64
     enclosures
    0.64
    PasswordEncoder
    0.63
     متعلقه
    0.63
    Activations Density 0.288%

    No Known Activations