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. 4-GEMMASCOPE-RES-16K
    6. 817
    Prev
    Next
    INDEX
    Explanations

    phrases indicating financial constraints or the inability to manage expenses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    выше
    -0.56
     مشين
    -0.55
    enumii
    -0.54
     зберіга
    -0.54
     متعلقه
    -0.53
     pinulongan
    -0.53
     acima
    -0.51
    OwnProperty
    -0.50
    estero
    -0.50
     سكانية
    -0.50
    POSITIVE LOGITS
     afford
    0.88
     resources
    0.84
    afford
    0.71
     ressources
    0.69
     moyens
    0.68
     RESOURCES
    0.67
     capabilities
    0.67
     resource
    0.65
     capability
    0.64
    resources
    0.64
    Activations Density 0.673%

    No Known Activations