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. 1-GEMMASCOPE-RES-16K
    6. 7110
    Prev
    Next
    INDEX
    Explanations

    instances of the word "necessary" and its context in discussions about conditions or requirements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MethodManager
    -0.87
    Personendaten
    -0.82
    GEBURTS
    -0.80
    IntoConstraints
    -0.79
    ViewImports
    -0.79
     كومونز
    -0.77
    ArrowToggle
    -0.72
    onViewCreated
    -0.71
     invokingState
    -0.70
     Administrativna
    -0.66
    POSITIVE LOGITS
    ə
    1.01
     necessary
    0.84
     evident
    0.64
    Necessary
    0.62
     desirable
    0.59
     Necessary
    0.58
    necessary
    0.57
     possible
    0.54
     jTextField
    0.54
     fair
    0.53
    Activations Density 0.055%

    No Known Activations