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. 2-GEMMASCOPE-RES-16K
    6. 15653
    Prev
    Next
    INDEX
    Explanations

    terms related to confidentiality and anonymity in various contexts

    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
     Winaray
    -0.70
    tadır
    -0.61
    enumi
    -0.60
     oprot
    -0.59
    LogFactory
    -0.59
     CORRE
    -0.59
     verwij
    -0.58
     rests
    -0.57
    uete
    -0.57
    itemBuilder
    -0.56
    POSITIVE LOGITS
    anonymous
    0.92
     Designated
    0.90
     designated
    0.88
    Designated
    0.83
     anonymous
    0.82
     designate
    0.75
     Specified
    0.75
    Anonymous
    0.75
    designated
    0.73
     Anonymous
    0.72
    Activations Density 0.133%

    No Known Activations