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. 14-GEMMASCOPE-RES-16K
    6. 10842
    Prev
    Next
    INDEX
    Explanations

    phrases related to restrictions or exclusions in contexts such as offers or eligibility criteria

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sterious
    -0.53
    acherous
    -0.52
    //
    -0.51
    claimer
    -0.51
     unlocked
    -0.51
    "),
    
    -0.49
    arder
    -0.49
    '],
    
    -0.48
     Avalanche
    -0.47
    muerzo
    -0.47
    POSITIVE LOGITS
    Hochspringen
    0.78
     محفوظة
    0.58
    InvalidProtocol
    0.57
    WithIOException
    0.56
    contentLoaded
    0.55
    TypedDataSet
    0.55
    原始内容存档于
    0.55
    QMetaType
    0.53
    borderBottom
    0.52
    mappedBy
    0.51
    Activations Density 0.551%

    No Known Activations