© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 3453
    Prev
    Next
    INDEX
    Explanations

    keywords related to security and data protection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iecie
    -0.62
    saraba
    -0.59
     UITableView
    -0.59
    mybatisplus
    -0.58
    CompilerServices
    -0.55
    MessageTagHelper
    -0.55
    tdessen
    -0.53
    twe
    -0.53
     findBy
    -0.53
    lappe
    -0.53
    POSITIVE LOGITS
     secure
    3.19
     Secure
    2.98
    Secure
    2.95
    secure
    2.90
     secured
    2.75
     secures
    2.51
     Secured
    2.46
     securing
    2.39
    secured
    2.39
    SECURE
    2.26
    Activations Density 0.058%

    No Known Activations