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. 17-GEMMASCOPE-RES-16K
    6. 9178
    Prev
    Next
    INDEX
    Explanations

    discussions about the regulation and control of internet content, especially related to child protection and terrorism

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyVersion
    -0.61
    endphp
    -0.59
     BoxFit
    -0.59
    )_/¯
    -0.58
     Voiture
    -0.56
    følgelig
    -0.53
    cerned
    -0.52
    reht
    -0.52
    guía
    -0.52
    oa̍t
    -0.51
    POSITIVE LOGITS
     online
    1.84
     Internet
    1.67
     internet
    1.67
     Online
    1.50
    Internet
    1.47
    internet
    1.42
    online
    1.42
    Online
    1.38
     web
    1.31
     ONLINE
    1.30
    Activations Density 0.616%

    No Known Activations